# Save Model Configuration V2 > PUT /api/v1/organizations/model-configurations/v2 — request parameters and responses from the Menace Voice API schema. `PUT /api/v1/organizations/model-configurations/v2` {/* Generated by scripts/sync_docs_api.mjs. Edit the API schema source to change the contract. */} See [authentication](/api-reference/authentication) for workspace API access. Public embed and artifact endpoints use their documented session or access tokens. ## API contract for documentation tools Generated from the OpenAPI schema. Do not infer a different parameter type from an example. Authentication headers are alternatives as explained in the authentication guide. ### Parameters | Name | Location | Type | Required | Description and constraints | | --- | --- | --- | --- | --- | | authorization | header | string or null | no | | | X-API-Key | header | string or null | no | | ### Request body: application/json Required body. Schema: OrganizationAIModelConfigurationV2 (object). | Field | Type | Required | Description and constraints | | --- | --- | --- | --- | | version | integer | no | default: 2 | | mode | string | yes | enum: ["dograh","byok"] | | dograh | DograhManagedAIModelConfiguration (object) or null | no | | | byok | BYOKAIModelConfiguration (object) or null | no | | ### Response 200 Successful Response application/json: OrganizationAIModelConfigurationResponse (object). | Field | Type | Required | Description and constraints | | --- | --- | --- | --- | | configuration | object or null | yes | | | effective_configuration | object | yes | | | source | string | yes | enum: ["organization_v2","legacy_user_v1","empty"] | ### Response 404 Not found ### Response 422 Validation Error application/json: HTTPValidationError (object). | Field | Type | Required | Description and constraints | | --- | --- | --- | --- | | detail | array of ValidationError (object) | no | | ## OpenAPI ````yaml api-reference/openapi.json put /api/v1/organizations/model-configurations/v2 openapi: 3.1.0 info: title: Menace Voice API description: API for Menace Voice agents version: 1.0.0 servers: - url: https://voice.menaceui.com description: Production - url: http://localhost:8000 description: Local development paths: /api/v1/organizations/model-configurations/v2: put: tags: - main - organizations summary: Save Model Configuration V2 operationId: save_model_configuration_v2_api_v1_organizations_model_configurations_v2_put parameters: - name: authorization in: header required: false schema: anyOf: - type: string - type: "null" title: Authorization - name: X-API-Key in: header required: false schema: anyOf: - type: string - type: "null" title: X-Api-Key requestBody: required: true content: application/json: schema: $ref: "#/components/schemas/OrganizationAIModelConfigurationV2" responses: "200": description: Successful Response content: application/json: schema: $ref: "#/components/schemas/OrganizationAIModelConfigurationResponse" "404": description: Not found "422": description: Validation Error content: application/json: schema: $ref: "#/components/schemas/HTTPValidationError" components: schemas: AWSBedrockLLMConfiguration: properties: provider: type: string const: aws_bedrock title: Provider default: aws_bedrock api_key: anyOf: - type: string - items: type: string type: array - type: "null" title: Api Key description: Not used for Bedrock — authentication is via the AWS credentials above. Leave blank. model: type: string title: Model description: Bedrock model ID — include the region inference-profile prefix (e.g. 'us.'). default: us.amazon.nova-pro-v1:0 examples: - us.amazon.nova-pro-v1:0 - us.amazon.nova-lite-v1:0 - us.amazon.nova-micro-v1:0 - us.anthropic.claude-sonnet-4-20250514-v1:0 - us.anthropic.claude-3-5-sonnet-20241022-v2:0 - us.anthropic.claude-haiku-4-5-20251001-v1:0 allow_custom_input: true aws_access_key: type: string title: Aws Access Key description: AWS access key ID with bedrock:InvokeModel permission. default: "" aws_secret_key: type: string title: Aws Secret Key description: AWS secret access key paired with the access key ID. default: "" aws_region: type: string title: Aws Region description: AWS region where the Bedrock model is available. default: us-east-1 type: object title: AWS Bedrock AssemblyAISTTConfiguration: properties: provider: type: string const: assemblyai title: Provider default: assemblyai api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: AssemblyAI realtime STT model. default: u3-rt-pro examples: - u3-rt-pro language: type: string title: Language description: ISO 639-1 language code. default: en examples: - en - es - de - fr - pt - it type: object required: - api_key title: AssemblyAI AtlasCloudLLMService: properties: provider: type: string const: atlascloud title: Provider default: atlascloud api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: Atlas Cloud OpenAI-compatible chat model identifier. default: qwen/qwen3.5-flash examples: - qwen/qwen3.5-flash - deepseek-ai/deepseek-v4-pro allow_custom_input: true base_url: type: string title: Base Url description: Atlas Cloud OpenAI-compatible API endpoint. default: https://api.atlascloud.ai/v1 type: object required: - api_key title: Atlas Cloud description: Atlas Cloud OpenAI-compatible LLM API. AzureLLMService: properties: provider: type: string const: azure title: Provider default: azure api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: Azure deployment name (not the upstream OpenAI model id). default: gpt-4.1-mini examples: - gpt-4.1-mini allow_custom_input: true endpoint: type: string title: Endpoint description: Azure OpenAI resource endpoint (e.g. https://.openai.azure.com). type: object required: - api_key - endpoint title: Azure OpenAI AzureOpenAIEmbeddingsConfiguration: properties: provider: type: string const: azure title: Provider default: azure api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: Azure OpenAI embedding deployment name. The deployment must return 1536-dimensional embeddings. default: text-embedding-3-small examples: - text-embedding-3-small - text-embedding-ada-002 allow_custom_input: true endpoint: type: string title: Endpoint description: Azure OpenAI resource endpoint (e.g. https://.openai.azure.com). api_version: type: string title: Api Version description: Azure OpenAI API version for embeddings. default: 2024-02-15-preview type: object required: - api_key - endpoint title: Azure OpenAI AzureRealtimeLLMConfiguration: properties: provider: type: string const: azure_realtime title: Provider default: azure_realtime api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: Azure OpenAI realtime deployment name. default: gpt-realtime examples: - gpt-realtime - gpt-realtime-1.5 - gpt-realtime-mini allow_custom_input: true endpoint: type: string title: Endpoint description: Azure OpenAI resource endpoint (e.g. https://.openai.azure.com). voice: type: string title: Voice description: Voice the model speaks in. default: alloy examples: - alloy - ash - ballad - coral - echo - sage - shimmer - verse allow_custom_input: true api_version: type: string title: Api Version description: Azure OpenAI Realtime protocol version. Use 'v1' for the GA API; date-based versions select the deprecated preview endpoint. default: v1 examples: - v1 - 2025-04-01-preview - 2024-10-01-preview - 2024-12-17 type: object required: - api_key - endpoint title: Azure OpenAI Realtime description: Azure OpenAI Realtime API — low-latency speech-to-speech conversations. provider_docs_url: https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/realtime-audio-quickstart AzureSpeechSTTConfiguration: properties: provider: type: string const: azure_speech title: Provider default: azure_speech api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: Azure Speech recognition model (use 'latest_long' for continuous recognition). default: latest_long examples: - latest_long - latest_short region: type: string title: Region description: Azure region for Speech Services (e.g. 'eastus', 'westeurope'). default: eastus examples: - eastus - eastus2 - westus - westus2 - westus3 - centralus - northcentralus - southcentralus - westcentralus - westeurope - northeurope - uksouth - ukwest - francecentral - switzerlandnorth - germanywestcentral - norwayeast - australiaeast - eastasia - southeastasia - japaneast - japanwest - koreacentral - centralindia - southindia - brazilsouth language: type: string title: Language description: BCP-47 language code for recognition. default: en-US examples: - en-US - en-GB - en-AU - en-CA - en-IN - es-ES - es-MX - fr-FR - fr-CA - de-DE - it-IT - ja-JP - ko-KR - zh-CN - pt-BR - pt-PT - ru-RU - ar-SA - nl-NL - pl-PL - hi-IN allow_custom_input: true type: object required: - api_key title: Azure Speech Services description: Azure Cognitive Services Speech — TTS and STT via the Azure Speech SDK. provider_docs_url: https://learn.microsoft.com/en-us/azure/ai-services/speech-service/ AzureSpeechTTSConfiguration: properties: provider: type: string const: azure_speech title: Provider default: azure_speech api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: Azure Speech synthesis engine (neural voices only). default: neural examples: - neural region: type: string title: Region description: Azure region for Speech Services (e.g. 'eastus', 'westeurope'). default: eastus examples: - eastus - eastus2 - westus - westus2 - westus3 - centralus - northcentralus - southcentralus - westcentralus - westeurope - northeurope - uksouth - ukwest - francecentral - switzerlandnorth - germanywestcentral - norwayeast - australiaeast - eastasia - southeastasia - japaneast - japanwest - koreacentral - centralindia - southindia - brazilsouth voice: type: string title: Voice description: Azure Neural voice name (e.g. 'en-US-AriaNeural'). default: en-US-AriaNeural examples: - en-US-AriaNeural - en-US-GuyNeural - en-US-JennyNeural - en-US-DavisNeural - en-US-AmberNeural - en-US-AnaNeural - en-US-AshleyNeural - en-US-BrandonNeural - en-US-ChristopherNeural - en-US-ElizabethNeural - en-US-EricNeural - en-US-JacobNeural - en-US-MichelleNeural - en-US-MonicaNeural - en-US-NancyNeural - en-US-RogerNeural - en-US-SaraNeural - en-US-SteffanNeural - en-US-TonyNeural allow_custom_input: true language: type: string title: Language description: BCP-47 language code for synthesis. default: en-US examples: - en-US - en-GB - en-AU - en-CA - en-IN - es-ES - es-MX - fr-FR - fr-CA - de-DE - it-IT - ja-JP - ko-KR - zh-CN - zh-HK - zh-TW - pt-BR - pt-PT - ru-RU - ar-SA - nl-NL - pl-PL - sv-SE - hi-IN allow_custom_input: true speed: type: number maximum: 2 minimum: 0.5 title: Speed description: Speech speed multiplier (0.5 to 2.0). default: 1 type: object required: - api_key title: Azure Speech Services description: Azure Cognitive Services Speech — TTS and STT via the Azure Speech SDK. provider_docs_url: https://learn.microsoft.com/en-us/azure/ai-services/speech-service/ BYOKAIModelConfiguration: properties: mode: type: string enum: - pipeline - realtime title: Mode pipeline: anyOf: - $ref: "#/components/schemas/BYOKPipelineAIModelConfiguration" - type: "null" realtime: anyOf: - $ref: "#/components/schemas/BYOKRealtimeAIModelConfiguration" - type: "null" type: object required: - mode title: BYOKAIModelConfiguration BYOKPipelineAIModelConfiguration: properties: llm: oneOf: - $ref: "#/components/schemas/OpenAILLMService" - $ref: "#/components/schemas/AtlasCloudLLMService" - $ref: "#/components/schemas/GoogleVertexLLMConfiguration" - $ref: "#/components/schemas/GroqLLMService" - $ref: "#/components/schemas/OpenRouterLLMConfiguration" - $ref: "#/components/schemas/GoogleLLMService" - $ref: "#/components/schemas/AzureLLMService" - $ref: "#/components/schemas/DograhLLMService" - $ref: "#/components/schemas/AWSBedrockLLMConfiguration" - $ref: "#/components/schemas/SpeachesLLMConfiguration" - $ref: "#/components/schemas/HuggingFaceLLMConfiguration" - $ref: "#/components/schemas/MiniMaxLLMConfiguration" - $ref: "#/components/schemas/SarvamLLMConfiguration" title: Llm discriminator: propertyName: provider mapping: atlascloud: "#/components/schemas/AtlasCloudLLMService" aws_bedrock: "#/components/schemas/AWSBedrockLLMConfiguration" azure: "#/components/schemas/AzureLLMService" dograh: "#/components/schemas/DograhLLMService" google: "#/components/schemas/GoogleLLMService" google_vertex: "#/components/schemas/GoogleVertexLLMConfiguration" groq: "#/components/schemas/GroqLLMService" huggingface: "#/components/schemas/HuggingFaceLLMConfiguration" minimax: "#/components/schemas/MiniMaxLLMConfiguration" openai: "#/components/schemas/OpenAILLMService" openrouter: "#/components/schemas/OpenRouterLLMConfiguration" sarvam: "#/components/schemas/SarvamLLMConfiguration" speaches: "#/components/schemas/SpeachesLLMConfiguration" tts: oneOf: - $ref: "#/components/schemas/DeepgramTTSConfiguration" - $ref: "#/components/schemas/GoogleTTSConfiguration" - $ref: "#/components/schemas/OpenAITTSService" - $ref: "#/components/schemas/ElevenlabsTTSConfiguration" - $ref: "#/components/schemas/CartesiaTTSConfiguration" - $ref: "#/components/schemas/InworldTTSConfiguration" - $ref: "#/components/schemas/DograhTTSService" - $ref: "#/components/schemas/SarvamTTSConfiguration" - $ref: "#/components/schemas/CambTTSConfiguration" - $ref: "#/components/schemas/RimeTTSConfiguration" - $ref: "#/components/schemas/SpeachesTTSConfiguration" - $ref: "#/components/schemas/MiniMaxTTSConfiguration" - $ref: "#/components/schemas/AzureSpeechTTSConfiguration" - $ref: "#/components/schemas/SmallestAITTSConfiguration" - $ref: "#/components/schemas/XAITTSConfiguration" - $ref: "#/components/schemas/LmntTTSConfiguration" title: Tts discriminator: propertyName: provider mapping: azure_speech: "#/components/schemas/AzureSpeechTTSConfiguration" camb: "#/components/schemas/CambTTSConfiguration" cartesia: "#/components/schemas/CartesiaTTSConfiguration" deepgram: "#/components/schemas/DeepgramTTSConfiguration" dograh: "#/components/schemas/DograhTTSService" elevenlabs: "#/components/schemas/ElevenlabsTTSConfiguration" google: "#/components/schemas/GoogleTTSConfiguration" inworld: "#/components/schemas/InworldTTSConfiguration" lmnt: "#/components/schemas/LmntTTSConfiguration" minimax: "#/components/schemas/MiniMaxTTSConfiguration" openai: "#/components/schemas/OpenAITTSService" rime: "#/components/schemas/RimeTTSConfiguration" sarvam: "#/components/schemas/SarvamTTSConfiguration" smallest: "#/components/schemas/SmallestAITTSConfiguration" speaches: "#/components/schemas/SpeachesTTSConfiguration" xai: "#/components/schemas/XAITTSConfiguration" stt: oneOf: - $ref: "#/components/schemas/DeepgramSTTConfiguration" - $ref: "#/components/schemas/CartesiaSTTConfiguration" - $ref: "#/components/schemas/OpenAISTTConfiguration" - $ref: "#/components/schemas/GoogleSTTConfiguration" - $ref: "#/components/schemas/DograhSTTService" - $ref: "#/components/schemas/SpeechmaticsSTTConfiguration" - $ref: "#/components/schemas/SarvamSTTConfiguration" - $ref: "#/components/schemas/SpeachesSTTConfiguration" - $ref: "#/components/schemas/HuggingFaceSTTConfiguration" - $ref: "#/components/schemas/AssemblyAISTTConfiguration" - $ref: "#/components/schemas/GladiaSTTConfiguration" - $ref: "#/components/schemas/AzureSpeechSTTConfiguration" - $ref: "#/components/schemas/SmallestAISTTConfiguration" - $ref: "#/components/schemas/ElevenlabsSTTConfiguration" title: Stt discriminator: propertyName: provider mapping: assemblyai: "#/components/schemas/AssemblyAISTTConfiguration" azure_speech: "#/components/schemas/AzureSpeechSTTConfiguration" cartesia: "#/components/schemas/CartesiaSTTConfiguration" deepgram: "#/components/schemas/DeepgramSTTConfiguration" dograh: "#/components/schemas/DograhSTTService" elevenlabs: "#/components/schemas/ElevenlabsSTTConfiguration" gladia: "#/components/schemas/GladiaSTTConfiguration" google: "#/components/schemas/GoogleSTTConfiguration" huggingface: "#/components/schemas/HuggingFaceSTTConfiguration" openai: "#/components/schemas/OpenAISTTConfiguration" sarvam: "#/components/schemas/SarvamSTTConfiguration" smallest: "#/components/schemas/SmallestAISTTConfiguration" speaches: "#/components/schemas/SpeachesSTTConfiguration" speechmatics: "#/components/schemas/SpeechmaticsSTTConfiguration" embeddings: anyOf: - oneOf: - $ref: "#/components/schemas/OpenAIEmbeddingsConfiguration" - $ref: "#/components/schemas/OpenRouterEmbeddingsConfiguration" - $ref: "#/components/schemas/AzureOpenAIEmbeddingsConfiguration" - $ref: "#/components/schemas/DograhEmbeddingsConfiguration" discriminator: propertyName: provider mapping: azure: "#/components/schemas/AzureOpenAIEmbeddingsConfiguration" dograh: "#/components/schemas/DograhEmbeddingsConfiguration" openai: "#/components/schemas/OpenAIEmbeddingsConfiguration" openrouter: "#/components/schemas/OpenRouterEmbeddingsConfiguration" - type: "null" title: Embeddings type: object required: - llm - tts - stt title: BYOKPipelineAIModelConfiguration BYOKRealtimeAIModelConfiguration: properties: realtime: oneOf: - $ref: "#/components/schemas/OpenAIRealtimeLLMConfiguration" - $ref: "#/components/schemas/GrokRealtimeLLMConfiguration" - $ref: "#/components/schemas/UltravoxRealtimeLLMConfiguration" - $ref: "#/components/schemas/GoogleRealtimeLLMConfiguration" - $ref: "#/components/schemas/GoogleVertexRealtimeLLMConfiguration" - $ref: "#/components/schemas/AzureRealtimeLLMConfiguration" title: Realtime discriminator: propertyName: provider mapping: azure_realtime: "#/components/schemas/AzureRealtimeLLMConfiguration" google_realtime: "#/components/schemas/GoogleRealtimeLLMConfiguration" google_vertex_realtime: "#/components/schemas/GoogleVertexRealtimeLLMConfiguration" grok_realtime: "#/components/schemas/GrokRealtimeLLMConfiguration" openai_realtime: "#/components/schemas/OpenAIRealtimeLLMConfiguration" ultravox_realtime: "#/components/schemas/UltravoxRealtimeLLMConfiguration" llm: oneOf: - $ref: "#/components/schemas/OpenAILLMService" - $ref: "#/components/schemas/AtlasCloudLLMService" - $ref: "#/components/schemas/GoogleVertexLLMConfiguration" - $ref: "#/components/schemas/GroqLLMService" - $ref: "#/components/schemas/OpenRouterLLMConfiguration" - $ref: "#/components/schemas/GoogleLLMService" - $ref: "#/components/schemas/AzureLLMService" - $ref: "#/components/schemas/DograhLLMService" - $ref: "#/components/schemas/AWSBedrockLLMConfiguration" - $ref: "#/components/schemas/SpeachesLLMConfiguration" - $ref: "#/components/schemas/HuggingFaceLLMConfiguration" - $ref: "#/components/schemas/MiniMaxLLMConfiguration" - $ref: "#/components/schemas/SarvamLLMConfiguration" title: Llm discriminator: propertyName: provider mapping: atlascloud: "#/components/schemas/AtlasCloudLLMService" aws_bedrock: "#/components/schemas/AWSBedrockLLMConfiguration" azure: "#/components/schemas/AzureLLMService" dograh: "#/components/schemas/DograhLLMService" google: "#/components/schemas/GoogleLLMService" google_vertex: "#/components/schemas/GoogleVertexLLMConfiguration" groq: "#/components/schemas/GroqLLMService" huggingface: "#/components/schemas/HuggingFaceLLMConfiguration" minimax: "#/components/schemas/MiniMaxLLMConfiguration" openai: "#/components/schemas/OpenAILLMService" openrouter: "#/components/schemas/OpenRouterLLMConfiguration" sarvam: "#/components/schemas/SarvamLLMConfiguration" speaches: "#/components/schemas/SpeachesLLMConfiguration" embeddings: anyOf: - oneOf: - $ref: "#/components/schemas/OpenAIEmbeddingsConfiguration" - $ref: "#/components/schemas/OpenRouterEmbeddingsConfiguration" - $ref: "#/components/schemas/AzureOpenAIEmbeddingsConfiguration" - $ref: "#/components/schemas/DograhEmbeddingsConfiguration" discriminator: propertyName: provider mapping: azure: "#/components/schemas/AzureOpenAIEmbeddingsConfiguration" dograh: "#/components/schemas/DograhEmbeddingsConfiguration" openai: "#/components/schemas/OpenAIEmbeddingsConfiguration" openrouter: "#/components/schemas/OpenRouterEmbeddingsConfiguration" - type: "null" title: Embeddings type: object required: - realtime - llm title: BYOKRealtimeAIModelConfiguration CambTTSConfiguration: properties: provider: type: string const: camb title: Provider default: camb api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: Camb.ai TTS model. default: mars-flash examples: - mars-flash - mars-pro - mars-instruct voice: type: string title: Voice description: Camb.ai voice ID. default: "147320" language: type: string title: Language description: BCP-47 language code. default: en-us type: object required: - api_key title: Camb.ai CartesiaSTTConfiguration: properties: provider: type: string const: cartesia title: Provider default: cartesia api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: Cartesia STT model. default: ink-whisper examples: - ink-2 - ink-whisper language: type: string title: Language description: ISO 639-1 language code. ink-2 currently supports English only. default: en examples: - en - zh - de - es - ru - ko - fr - ja - pt - tr - pl - ca - nl - ar - sv - it - id - hi - fi - vi - he - uk - el - ms - cs - ro - da - hu - ta - no - th - ur - hr - bg - lt - la - mi - ml - cy - sk - te - fa - lv - bn - sr - az - sl - kn - et - mk - br - eu - is - hy - ne - mn - bs - kk - sq - sw - gl - mr - pa - si - km - sn - yo - so - af - oc - ka - be - tg - sd - gu - am - yi - lo - uz - fo - ht - ps - tk - nn - mt - sa - lb - my - bo - tl - mg - as - tt - haw - ln - ha - ba - jw - su - yue model_options: ink-2: - en ink-whisper: - en - zh - de - es - ru - ko - fr - ja - pt - tr - pl - ca - nl - ar - sv - it - id - hi - fi - vi - he - uk - el - ms - cs - ro - da - hu - ta - no - th - ur - hr - bg - lt - la - mi - ml - cy - sk - te - fa - lv - bn - sr - az - sl - kn - et - mk - br - eu - is - hy - ne - mn - bs - kk - sq - sw - gl - mr - pa - si - km - sn - yo - so - af - oc - ka - be - tg - sd - gu - am - yi - lo - uz - fo - ht - ps - tk - nn - mt - sa - lb - my - bo - tl - mg - as - tt - haw - ln - ha - ba - jw - su - yue type: object required: - api_key title: Cartesia CartesiaTTSConfiguration: properties: provider: type: string const: cartesia title: Provider default: cartesia api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: Cartesia TTS model. default: sonic-3.5 examples: - sonic-3.5 - sonic-3 voice: type: string title: Voice description: Cartesia voice UUID from your Cartesia dashboard. default: 3faa81ae-d3d8-4ab1-9e44-e50e46d33c30 speed: type: number maximum: 1.5 minimum: 0.6 title: Speed description: Speed of the voice. default: 1 volume: type: number maximum: 2 minimum: 0.5 title: Volume description: Volume multiplier for generated speech. default: 1 language: type: string title: Language description: Cartesia language code for TTS synthesis (e.g. 'en', 'tr', 'fr', 'de'). default: en allow_custom_input: true type: object required: - api_key title: Cartesia DeepgramSTTConfiguration: properties: provider: type: string const: deepgram title: Provider default: deepgram api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: Deepgram STT model. default: nova-3-general examples: - nova-3-general - nova-3-medical - flux-general-en - flux-general-multi allow_custom_input: true language: type: string title: Language description: Language code. 'multi' enables Nova-3 auto-detect and omits language hints for Flux multilingual auto-detect. default: multi examples: - multi - ar - ar-AE - ar-SA - ar-QA - ar-KW - ar-SY - ar-LB - ar-PS - ar-JO - ar-EG - ar-SD - ar-TD - ar-MA - ar-DZ - ar-TN - ar-IQ - ar-IR - be - bn - bs - bg - ca - cs - da - da-DK - de - de-CH - el - en - en-US - en-AU - en-GB - en-IN - en-NZ - es - es-419 - et - fa - fi - fr - fr-CA - he - hi - hr - hu - id - it - ja - kn - ko - ko-KR - lt - lv - mk - mr - ms - nl - nl-BE - no - pl - pt - pt-BR - pt-PT - ro - ru - sk - sl - sr - sv - sv-SE - ta - te - th - tl - tr - uk - ur - vi - zh-CN - zh-TW allow_custom_input: true model_options: flux-general-en: - en flux-general-multi: - multi - de - en - es - fr - hi - it - ja - nl - pt - ru nova-3-general: - multi - ar - ar-AE - ar-SA - ar-QA - ar-KW - ar-SY - ar-LB - ar-PS - ar-JO - ar-EG - ar-SD - ar-TD - ar-MA - ar-DZ - ar-TN - ar-IQ - ar-IR - be - bn - bs - bg - ca - cs - da - da-DK - de - de-CH - el - en - en-US - en-AU - en-GB - en-IN - en-NZ - es - es-419 - et - fa - fi - fr - fr-CA - he - hi - hr - hu - id - it - ja - kn - ko - ko-KR - lt - lv - mk - mr - ms - nl - nl-BE - no - pl - pt - pt-BR - pt-PT - ro - ru - sk - sl - sr - sv - sv-SE - ta - te - th - tl - tr - uk - ur - vi - zh-CN - zh-TW nova-3-medical: - multi - ar - ar-AE - ar-SA - ar-QA - ar-KW - ar-SY - ar-LB - ar-PS - ar-JO - ar-EG - ar-SD - ar-TD - ar-MA - ar-DZ - ar-TN - ar-IQ - ar-IR - be - bn - bs - bg - ca - cs - da - da-DK - de - de-CH - el - en - en-US - en-AU - en-GB - en-IN - en-NZ - es - es-419 - et - fa - fi - fr - fr-CA - he - hi - hr - hu - id - it - ja - kn - ko - ko-KR - lt - lv - mk - mr - ms - nl - nl-BE - no - pl - pt - pt-BR - pt-PT - ro - ru - sk - sl - sr - sv - sv-SE - ta - te - th - tl - tr - uk - ur - vi - zh-CN - zh-TW type: object required: - api_key title: Deepgram DeepgramTTSConfiguration: properties: provider: type: string const: deepgram title: Provider default: deepgram api_key: anyOf: - type: string - items: type: string type: array title: Api Key voice: type: string title: Voice description: Deepgram voice ID (model is inferred from the 'aura-N' prefix). default: aura-2-helena-en type: object required: - api_key title: Deepgram DograhEmbeddingsConfiguration: properties: provider: type: string const: dograh title: Provider default: dograh api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: Menace Voice-managed embedding model. default: dograh_embedding_v1 examples: - dograh_embedding_v1 type: object required: - api_key title: Menace Voice DograhLLMService: properties: provider: type: string const: dograh title: Provider default: dograh api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: Menace Voice-hosted model tier. default: default examples: - default - accurate - fast - lite - zen allow_custom_input: true type: object required: - api_key title: Menace Voice DograhManagedAIModelConfiguration: properties: api_key: type: string title: Api Key voice: type: string title: Voice default: default speed: type: number maximum: 2 minimum: 0.5 title: Speed default: 1 language: type: string title: Language default: multi type: object required: - api_key title: DograhManagedAIModelConfiguration DograhSTTService: properties: provider: type: string const: dograh title: Provider default: dograh api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: Menace Voice STT tier. default: default examples: - default language: type: string title: Language description: Language code; use 'multi' for auto-detect. default: multi examples: - multi - ar - ar-AE - ar-SA - ar-QA - ar-KW - ar-SY - ar-LB - ar-PS - ar-JO - ar-EG - ar-SD - ar-TD - ar-MA - ar-DZ - ar-TN - ar-IQ - ar-IR - be - bn - bs - bg - ca - cs - da - da-DK - de - de-CH - el - en - en-US - en-AU - en-GB - en-IN - en-NZ - es - es-419 - et - fa - fi - fr - fr-CA - he - hi - hr - hu - id - it - ja - kn - ko - ko-KR - lt - lv - mk - mr - ms - nl - nl-BE - no - pl - pt - pt-BR - pt-PT - ro - ru - sk - sl - sr - sv - sv-SE - ta - te - th - tl - tr - uk - ur - vi - zh-CN - zh-TW type: object required: - api_key title: Menace Voice DograhTTSService: properties: provider: type: string const: dograh title: Provider default: dograh api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: Menace Voice TTS tier. default: default examples: - default voice: type: string title: Voice description: Voice preset. default: default allow_custom_input: true speed: type: number maximum: 2 minimum: 0.5 title: Speed description: Speed of the voice. default: 1 type: object required: - api_key title: Menace Voice ElevenlabsSTTConfiguration: properties: provider: type: string const: elevenlabs title: Provider default: elevenlabs api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: ElevenLabs realtime STT model. default: scribe_v2_realtime examples: - scribe_v2_realtime allow_custom_input: true language: type: string title: Language description: ISO 639-1 language code for transcription. Use 'auto' to let ElevenLabs detect the language. default: en examples: - auto - af - am - ar - as - az - be - bg - bn - bs - ca - ceb - cs - cy - da - de - el - en - es - et - fa - fi - fil - fr - ga - gl - gu - ha - he - hi - hr - hu - hy - id - ig - is - it - ja - jv - ka - kk - km - kn - ko - ku - ky - lo - lt - lv - mi - mk - ml - mn - mr - ms - mt - my - ne - nl - no - ny - oc - or - pa - pl - ps - pt - ro - ru - sd - sk - sl - sn - so - sr - sv - sw - ta - te - tg - th - tr - uk - ur - uz - vi - wo - xh - yue - zh - zu allow_custom_input: true base_url: type: string title: Base Url description: ElevenLabs API base URL. Override to use a Data Residency endpoint (e.g. https://api.eu.residency.elevenlabs.io) for GDPR / HIPAA / regional compliance. default: https://api.elevenlabs.io type: object required: - api_key title: ElevenLabs ElevenlabsTTSConfiguration: properties: provider: type: string const: elevenlabs title: Provider default: elevenlabs api_key: anyOf: - type: string - items: type: string type: array title: Api Key voice: type: string title: Voice description: ElevenLabs voice ID from your Voice Library. default: 21m00Tcm4TlvDq8ikWAM speed: type: number maximum: 2 minimum: 0.1 title: Speed description: Speed of the voice. default: 1 model: type: string title: Model description: ElevenLabs TTS model. default: eleven_flash_v2_5 examples: - eleven_flash_v2_5 allow_custom_input: true base_url: type: string title: Base Url description: ElevenLabs API base URL. Override to use a Data Residency endpoint (e.g. https://api.eu.residency.elevenlabs.io) for GDPR / HIPAA / regional compliance. default: https://api.elevenlabs.io type: object required: - api_key title: ElevenLabs GladiaSTTConfiguration: properties: provider: type: string const: gladia title: Provider default: gladia api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: Gladia STT model. default: solaria-1 examples: - solaria-1 language: type: string title: Language description: ISO 639-1 language code. default: en examples: - af - am - ar - as - az - ba - be - bg - bn - bo - br - bs - ca - cs - cy - da - de - el - en - es - et - eu - fa - fi - fo - fr - gl - gu - ha - haw - he - hi - hr - ht - hu - hy - id - is - it - ja - jw - ka - kk - km - kn - ko - la - lb - ln - lo - lt - lv - mg - mi - mk - ml - mn - mr - ms - mt - my - ne - nl - nn - no - oc - pa - pl - ps - pt - ro - ru - sa - sd - si - sk - sl - sn - so - sq - sr - su - sv - sw - ta - te - tg - th - tk - tl - tr - tt - uk - ur - uz - vi - wo - yi - yo - zh type: object required: - api_key title: Gladia GoogleLLMService: properties: provider: type: string const: google title: Provider default: google api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: Gemini model on Google AI Studio (not Vertex). default: gemini-3.5-flash examples: - gemini-3.5-flash - gemini-3.5-flash-lite allow_custom_input: true type: object required: - api_key title: Google GoogleRealtimeLLMConfiguration: properties: provider: type: string const: google_realtime title: Provider default: google_realtime api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: Gemini Live model on Google AI Studio (not Vertex). default: gemini-3.1-flash-live-preview examples: - gemini-3.1-flash-live-preview allow_custom_input: true voice: type: string title: Voice description: Voice the model speaks in. default: Puck examples: - Puck - Charon - Kore - Fenrir - Aoede allow_custom_input: true language: type: string title: Language description: ISO 639-1 language code. default: en examples: - ar - bn - de - en - es - fr - gu - hi - id - it - ja - kn - ko - ml - mr - nl - pl - pt - ru - ta - te - th - tr - vi - zh allow_custom_input: true temperature: anyOf: - type: number maximum: 2 minimum: 0 - type: "null" title: Temperature description: Sampling temperature for Gemini Live (0.0 to 2.0). type: object required: - api_key title: Google Realtime GoogleSTTConfiguration: properties: provider: type: string const: google title: Provider default: google api_key: anyOf: - type: string - items: type: string type: array - type: "null" title: Api Key description: Not used for Google Cloud STT. Leave blank. model: type: string title: Model description: Google Cloud Speech-to-Text V2 recognition model. default: latest_long examples: - latest_long - latest_short - chirp_3 allow_custom_input: true language: type: string title: Language description: Primary BCP-47 language code for recognition. default: en-US examples: - af-ZA - am-ET - ar-AE - ar-BH - ar-DZ - ar-EG - ar-IL - ar-IQ - ar-JO - ar-KW - ar-LB - ar-MA - ar-MR - ar-OM - ar-PS - ar-QA - ar-SA - ar-SY - ar-TN - ar-XA - ar-YE - as-IN - ast-ES - az-AZ - be-BY - bg-BG - bn-BD - bn-IN - bs-BA - ca-ES - ceb-PH - ckb-IQ - cmn-Hans-CN - cmn-Hant-TW - cs-CZ - cy-GB - da-DK - de-AT - de-CH - de-DE - el-GR - en-AU - en-GB - en-HK - en-IE - en-IN - en-NZ - en-PH - en-PK - en-SG - en-US - es-419 - es-AR - es-BO - es-CL - es-CO - es-CR - es-DO - es-EC - es-ES - es-GT - es-HN - es-MX - es-NI - es-PA - es-PE - es-PR - es-SV - es-US - es-UY - es-VE - et-EE - eu-ES - fa-IR - ff-SN - fi-FI - fil-PH - fr-BE - fr-CA - fr-CH - fr-FR - ga-IE - gl-ES - gu-IN - ha-NG - hi-IN - hr-HR - hu-HU - hy-AM - id-ID - ig-NG - is-IS - it-CH - it-IT - iw-IL - ja-JP - jv-ID - ka-GE - kam-KE - kea-CV - kk-KZ - km-KH - kn-IN - ko-KR - ky-KG - lb-LU - lg-UG - ln-CD - lo-LA - lt-LT - luo-KE - lv-LV - mi-NZ - mk-MK - ml-IN - mn-MN - mr-IN - ms-MY - mt-MT - my-MM - ne-NP - nl-BE - nl-NL - no-NO - nso-ZA - ny-MW - oc-FR - om-ET - or-IN - pa-Guru-IN - pl-PL - ps-AF - pt-BR - pt-PT - ro-RO - ru-RU - rup-BG - rw-RW - sd-IN - si-LK - sk-SK - sl-SI - sn-ZW - so-SO - sq-AL - sr-RS - ss-Latn-ZA - st-ZA - su-ID - sv-SE - sw - sw-KE - ta-IN - te-IN - tg-TJ - th-TH - tn-Latn-ZA - tr-TR - ts-ZA - uk-UA - umb-AO - ur-PK - uz-UZ - ve-ZA - vi-VN - wo-SN - xh-ZA - yo-NG - yue-Hant-HK - zu-ZA allow_custom_input: true docs_url: https://docs.cloud.google.com/speech-to-text/docs/speech-to-text-supported-languages location: type: string title: Location description: Google Cloud Speech-to-Text region (for example 'global' or 'us-central1'). default: global credentials: anyOf: - type: string - type: "null" title: Credentials description: Paste the entire Google Cloud service-account JSON. If omitted, the server falls back to Application Default Credentials (ADC). multiline: true type: object title: Google Cloud GoogleTTSConfiguration: properties: provider: type: string const: google title: Provider default: google api_key: anyOf: - type: string - items: type: string type: array - type: "null" title: Api Key description: Not used for Google Cloud TTS. Leave blank. model: type: string title: Model description: Google Cloud low-latency TTS engine. Dograh maps this to Pipecat's streaming Google TTS service for Chirp 3 HD and Journey voices. default: chirp_3_hd examples: - chirp_3_hd allow_custom_input: true voice: type: string title: Voice description: Google Cloud voice name. Use a Chirp 3 HD or Journey voice for streaming TTS. default: en-US-Chirp3-HD-Charon examples: - en-US-Chirp3-HD-Charon allow_custom_input: true language: type: string title: Language description: BCP-47 language code for synthesis. default: en-US examples: - ar-XA - bn-IN - bg-BG - yue-HK - hr-HR - cs-CZ - da-DK - nl-BE - nl-NL - en-AU - en-IN - en-GB - en-US - et-EE - fi-FI - fr-CA - fr-FR - de-DE - el-GR - gu-IN - he-IL - hi-IN - hu-HU - id-ID - it-IT - ja-JP - kn-IN - ko-KR - lv-LV - lt-LT - ml-IN - cmn-CN - mr-IN - nb-NO - pl-PL - pt-BR - pa-IN - ro-RO - ru-RU - sr-RS - sk-SK - sl-SI - es-ES - es-US - sw-KE - sv-SE - ta-IN - te-IN - th-TH - tr-TR - uk-UA - ur-IN - vi-VN allow_custom_input: true speed: type: number maximum: 2 minimum: 0.25 title: Speed description: Speech speed multiplier for Google streaming TTS. default: 1 location: anyOf: - type: string - type: "null" title: Location description: Optional Google Cloud regional Text-to-Speech endpoint (for example 'us-central1'). Leave blank to use the default endpoint. credentials: anyOf: - type: string - type: "null" title: Credentials description: Paste the entire Google Cloud service-account JSON. If omitted, the server falls back to Application Default Credentials (ADC). multiline: true type: object title: Google Cloud GoogleVertexLLMConfiguration: properties: provider: type: string const: google_vertex title: Provider default: google_vertex api_key: anyOf: - type: string - items: type: string type: array - type: "null" title: Api Key description: Not used for Vertex AI — authentication is via the service account in `credentials` (or ADC). Leave blank. model: type: string title: Model description: Gemini model on Vertex AI. default: gemini-3.5-flash examples: - gemini-3.1-flash-lite - gemini-3.5-flash - gemini-3.5-flash-lite allow_custom_input: true project_id: type: string title: Project Id description: Google Cloud project ID for Vertex AI. location: type: string title: Location description: GCP region for the Vertex AI endpoint (e.g. 'global'). default: global credentials: anyOf: - type: string - type: "null" title: Credentials description: Paste the entire service-account JSON file contents. If omitted, falls back to Application Default Credentials (ADC). multiline: true type: object required: - project_id title: Google Vertex GoogleVertexRealtimeLLMConfiguration: properties: provider: type: string const: google_vertex_realtime title: Provider default: google_vertex_realtime api_key: anyOf: - type: string - items: type: string type: array - type: "null" title: Api Key description: Not used for Vertex AI — authentication is via the service account in `credentials` (or ADC). Leave blank. model: type: string title: Model description: Vertex AI publisher/model identifier. default: google/gemini-live-2.5-flash-native-audio examples: - google/gemini-live-2.5-flash-native-audio allow_custom_input: true voice: type: string title: Voice description: Voice the model speaks in. default: Charon examples: - Puck - Charon - Kore - Fenrir - Aoede allow_custom_input: true language: type: string title: Language description: BCP-47 language code (e.g. 'en-US'). default: en examples: - ar - bn - de - en - es - fr - gu - hi - id - it - ja - kn - ko - ml - mr - nl - pl - pt - ru - ta - te - th - tr - vi - zh allow_custom_input: true temperature: anyOf: - type: number maximum: 2 minimum: 0 - type: "null" title: Temperature description: Sampling temperature for Gemini Live (0.0 to 2.0). project_id: type: string title: Project Id description: Google Cloud project ID for Vertex AI. location: type: string title: Location description: GCP region for the Vertex AI endpoint (e.g. 'global'). default: global credentials: anyOf: - type: string - type: "null" title: Credentials description: Paste the entire service-account JSON file contents. If omitted, falls back to Application Default Credentials (ADC). multiline: true type: object required: - project_id title: Google Vertex Realtime GrokRealtimeLLMConfiguration: properties: provider: type: string const: grok_realtime title: Provider default: grok_realtime api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: Grok realtime voice-agent model. default: grok-voice-think-fast-1.0 examples: - grok-voice-think-fast-1.0 allow_custom_input: true voice: type: string title: Voice description: Voice the model speaks in. default: ara examples: - ara - rex - sal - eve - leo allow_custom_input: true type: object required: - api_key title: Grok Realtime GroqLLMService: properties: provider: type: string const: groq title: Provider default: groq api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: Groq-hosted model identifier. default: llama-3.3-70b-versatile examples: - llama-3.3-70b-versatile - deepseek-r1-distill-llama-70b - qwen-qwq-32b - meta-llama/llama-4-scout-17b-16e-instruct - meta-llama/llama-4-maverick-17b-128e-instruct - gemma2-9b-it - llama-3.1-8b-instant - openai/gpt-oss-120b allow_custom_input: true type: object required: - api_key title: Groq HTTPValidationError: properties: detail: items: $ref: "#/components/schemas/ValidationError" type: array title: Detail type: object title: HTTPValidationError HuggingFaceLLMConfiguration: properties: provider: type: string const: huggingface title: Provider default: huggingface api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: Hugging Face chat-completion model identifier, optionally with provider suffix. default: openai/gpt-oss-120b:cerebras examples: - openai/gpt-oss-120b:cerebras - deepseek-ai/DeepSeek-R1:fastest - Qwen/Qwen3-Coder-480B-A35B-Instruct:fastest allow_custom_input: true base_url: type: string title: Base Url description: Hugging Face OpenAI-compatible chat-completions router base URL. default: https://router.huggingface.co/v1 bill_to: anyOf: - type: string - type: "null" title: Bill To description: Optional Hugging Face organization or user to bill using X-HF-Bill-To. type: object required: - api_key title: Hugging Face description: Hosted Hugging Face Inference Providers API for usage-based inference. provider_docs_url: https://huggingface.co/docs/inference-providers/en/index HuggingFaceSTTConfiguration: properties: provider: type: string const: huggingface title: Provider default: huggingface api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: Hugging Face ASR model identifier served through Inference Providers. default: openai/whisper-large-v3-turbo examples: - openai/whisper-large-v3-turbo - openai/whisper-large-v3 allow_custom_input: true base_url: type: string title: Base Url description: Hugging Face Inference Providers router base URL. default: https://router.huggingface.co/hf-inference bill_to: anyOf: - type: string - type: "null" title: Bill To description: Optional Hugging Face organization or user to bill using X-HF-Bill-To. return_timestamps: type: boolean title: Return Timestamps description: Request timestamp chunks when supported by the selected provider/model. default: false type: object required: - api_key title: Hugging Face description: Hosted Hugging Face Inference Providers API for usage-based inference. provider_docs_url: https://huggingface.co/docs/inference-providers/en/index InworldTTSConfiguration: properties: provider: type: string const: inworld title: Provider default: inworld api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: Inworld TTS model. default: inworld-tts-2 examples: - inworld-tts-2 allow_custom_input: true voice: type: string title: Voice description: Inworld voice ID. Use Ashley for the default warm English voice, or a workspace voice ID for a cloned/custom voice. default: Ashley examples: - Ashley allow_custom_input: true language: type: string title: Language description: BCP-47 language code for synthesis. default: en-US examples: - en-US allow_custom_input: true speed: type: number maximum: 4 minimum: 0.25 title: Speed description: Speech speed multiplier. default: 1 delivery_mode: type: string enum: - STABLE - BALANCED - CREATIVE title: Delivery Mode description: Controls stability versus expressiveness for inworld-tts-2 (STABLE, BALANCED, or CREATIVE). default: BALANCED type: object required: - api_key title: Inworld description: Inworld AI streaming text-to-speech with built-in and cloned voices. Defaults to the Ashley system voice on inworld-tts-2. provider_docs_url: https://docs.inworld.ai/tts/tts LmntTTSConfiguration: properties: provider: type: string const: lmnt title: Provider default: lmnt api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: LMNT TTS model. 'aurora' is the general-purpose model; 'blizzard' targets more expressive, conversational speech. default: aurora examples: - aurora - blizzard voice: type: string title: Voice description: LMNT voice ID. Use a stock voice name or a custom voice ID from your LMNT account. default: lily examples: - lily - daniel - ava - caleb - leah - zeke allow_custom_input: true language: type: string title: Language description: Language code for synthesis (e.g. 'en', 'es', 'fr', 'de', 'pt', 'zh', 'ko', 'hi'). default: en allow_custom_input: true type: object required: - api_key title: LMNT MiniMaxLLMConfiguration: properties: provider: type: string const: minimax title: Provider default: minimax api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: MiniMax chat model. default: MiniMax-M2.7 examples: - MiniMax-M2.7 - MiniMax-M2.7-highspeed - MiniMax-M3 allow_custom_input: true base_url: type: string title: Base Url description: MiniMax OpenAI-compatible API endpoint. default: https://api.minimax.io/v1 temperature: type: number maximum: 2 exclusiveMinimum: 0 title: Temperature description: Sampling temperature. MiniMax requires > 0. default: 1 type: object required: - api_key title: MiniMaxLLMConfiguration MiniMaxTTSConfiguration: properties: provider: type: string const: minimax title: Provider default: minimax api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: MiniMax TTS model. default: speech-2.8-hd examples: - speech-2.8-hd - speech-2.8-turbo voice: type: string title: Voice description: MiniMax voice ID. default: English_Graceful_Lady examples: - English_Graceful_Lady - English_Insightful_Speaker - English_radiant_girl - English_Persuasive_Man - English_Lucky_Robot - English_expressive_narrator allow_custom_input: true base_url: type: string title: Base Url description: MiniMax TTS API endpoint (must include the /v1/t2a_v2 path). Defaults to the global endpoint; override with https://api.minimaxi.chat/v1/t2a_v2 (mainland China) or https://api-uw.minimax.io/v1/t2a_v2 (US-West). default: https://api.minimax.io/v1/t2a_v2 speed: type: number maximum: 2 minimum: 0.5 title: Speed description: Speech speed (0.5 to 2.0). default: 1 group_id: type: string title: Group Id description: MiniMax Group ID (found in your MiniMax dashboard under Account → Group). type: object required: - api_key - group_id title: MiniMaxTTSConfiguration OpenAIEmbeddingsConfiguration: properties: provider: type: string const: openai title: Provider default: openai api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: OpenAI embedding model. default: text-embedding-3-small examples: - text-embedding-3-small type: object required: - api_key title: OpenAI OpenAILLMService: properties: provider: type: string const: openai title: Provider default: openai api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: OpenAI chat model to use. default: gpt-4.1 examples: - gpt-4.1 - gpt-4.1-mini - gpt-4.1-nano - gpt-5 - gpt-5-mini - gpt-5-nano - gpt-3.5-turbo allow_custom_input: true base_url: type: string title: Base Url description: Override only if using an OpenAI-compatible API (e.g. local LLM, proxy). default: https://api.openai.com/v1 type: object required: - api_key title: OpenAI OpenAIRealtimeLLMConfiguration: properties: provider: type: string const: openai_realtime title: Provider default: openai_realtime api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: OpenAI realtime (speech-to-speech) model. default: gpt-realtime-2 examples: - gpt-realtime-2 allow_custom_input: true voice: type: string title: Voice description: Voice the model speaks in. default: alloy examples: - alloy - ash - ballad - coral - echo - sage - shimmer - verse allow_custom_input: true language: anyOf: - type: string - type: "null" title: Language description: ISO 639-1 language code for input audio transcription (e.g. 'pt', 'es'). Improves transcription accuracy and latency. Leave unset to auto-detect. examples: - en - es - pt - fr - de - it - hi - ja - ko - zh allow_custom_input: true type: object required: - api_key title: OpenAI Realtime OpenAISTTConfiguration: properties: provider: type: string const: openai title: Provider default: openai api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: OpenAI transcription model. default: gpt-4o-transcribe examples: - gpt-4o-transcribe base_url: type: string title: Base Url description: Override only if using an OpenAI-compatible API (e.g. local STT, proxy). default: https://api.openai.com/v1 type: object required: - api_key title: OpenAI OpenAITTSService: properties: provider: type: string const: openai title: Provider default: openai api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: OpenAI TTS model. default: gpt-4o-mini-tts examples: - gpt-4o-mini-tts voice: type: string title: Voice description: OpenAI TTS voice name. default: alloy base_url: type: string title: Base Url description: Override only if using an OpenAI-compatible API (e.g. local TTS, proxy). default: https://api.openai.com/v1 type: object required: - api_key title: OpenAI OpenRouterEmbeddingsConfiguration: properties: provider: type: string const: openrouter title: Provider default: openrouter api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: OpenRouter-hosted embedding model slug. default: openai/text-embedding-3-small examples: - openai/text-embedding-3-small base_url: type: string title: Base Url description: Override only if proxying OpenRouter through your own gateway. default: https://openrouter.ai/api/v1 type: object required: - api_key title: Open Router OpenRouterLLMConfiguration: properties: provider: type: string const: openrouter title: Provider default: openrouter api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: OpenRouter model slug in 'vendor/model' form. default: openai/gpt-4.1 examples: - openai/gpt-4.1 - openai/gpt-4.1-mini - anthropic/claude-sonnet-4 - google/gemini-2.5-flash - meta-llama/llama-3.3-70b-instruct - deepseek/deepseek-chat-v3-0324 allow_custom_input: true base_url: type: string title: Base Url description: Override only if proxying OpenRouter through your own gateway. default: https://openrouter.ai/api/v1 type: object required: - api_key title: Open Router OrganizationAIModelConfigurationResponse: properties: configuration: anyOf: - additionalProperties: true type: object - type: "null" title: Configuration effective_configuration: additionalProperties: true type: object title: Effective Configuration source: type: string enum: - organization_v2 - legacy_user_v1 - empty title: Source type: object required: - configuration - effective_configuration - source title: OrganizationAIModelConfigurationResponse OrganizationAIModelConfigurationV2: properties: version: type: integer const: 2 title: Version default: 2 mode: type: string enum: - dograh - byok title: Mode dograh: anyOf: - $ref: "#/components/schemas/DograhManagedAIModelConfiguration" - type: "null" byok: anyOf: - $ref: "#/components/schemas/BYOKAIModelConfiguration" - type: "null" type: object required: - mode title: OrganizationAIModelConfigurationV2 RimeTTSConfiguration: properties: provider: type: string const: rime title: Provider default: rime api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: Rime TTS model. default: arcana examples: - arcana - mistv3 - mistv2 - mist allow_custom_input: true voice: type: string title: Voice description: Rime voice ID. default: celeste speed: type: number maximum: 2 minimum: 0.5 title: Speed description: Speech speed multiplier. default: 1 language: type: string title: Language description: ISO 639-1 language code. default: en examples: - en - de - fr - es - hi allow_custom_input: true type: object required: - api_key title: Rime SarvamLLMConfiguration: properties: provider: type: string const: sarvam title: Provider default: sarvam api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: Sarvam chat model. default: sarvam-105b examples: - sarvam-105b allow_custom_input: true temperature: type: number maximum: 2 minimum: 0 title: Temperature description: Sampling temperature. Sarvam recommends 0.5 for balanced conversational responses. default: 0.5 type: object required: - api_key title: Sarvam SarvamSTTConfiguration: properties: provider: type: string const: sarvam title: Provider default: sarvam api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: Sarvam STT model. saarika:v2.5 transcribes in the spoken language; saaras:v3 is the recommended model with flexible output modes. default: saarika:v2.5 examples: - saarika:v2.5 - saaras:v3 language: type: string title: Language description: BCP-47 language code. Use unknown for automatic language detection. default: unknown examples: - unknown - hi-IN - bn-IN - gu-IN - kn-IN - ml-IN - mr-IN - od-IN - pa-IN - ta-IN - te-IN - en-IN model_options: saaras:v3: - unknown - hi-IN - bn-IN - gu-IN - kn-IN - ml-IN - mr-IN - od-IN - pa-IN - ta-IN - te-IN - en-IN - as-IN - ur-IN - ne-IN - kok-IN - ks-IN - sd-IN - sa-IN - sat-IN - mni-IN - brx-IN - mai-IN - doi-IN saarika:v2.5: - unknown - hi-IN - bn-IN - gu-IN - kn-IN - ml-IN - mr-IN - od-IN - pa-IN - ta-IN - te-IN - en-IN type: object required: - api_key title: Sarvam SarvamTTSConfiguration: properties: provider: type: string const: sarvam title: Provider default: sarvam api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: Sarvam TTS model (voice list depends on this). default: bulbul:v2 examples: - bulbul:v2 - bulbul:v3 voice: type: string title: Voice description: Sarvam voice name or custom voice ID. default: anushka examples: - anushka - manisha - vidya - arya - abhilash - karun - hitesh allow_custom_input: true model_options: bulbul:v2: - anushka - manisha - vidya - arya - abhilash - karun - hitesh bulbul:v3: - shubh - aditya - ritu - priya - neha - rahul - pooja - rohan - simran - kavya - amit - dev - ishita - shreya - ratan - varun - manan - sumit - roopa - kabir - aayan - ashutosh - advait - amelia - sophia - anand - tanya - tarun - sunny - mani - gokul - vijay - shruti - suhani - mohit - kavitha - rehan - soham - rupali language: type: string title: Language description: BCP-47 Indian-language code (e.g. hi-IN, en-IN). default: hi-IN examples: - bn-IN - en-IN - gu-IN - hi-IN - kn-IN - ml-IN - mr-IN - od-IN - pa-IN - ta-IN - te-IN - as-IN speed: type: number maximum: 2 minimum: 0.5 title: Speed description: Speech speed multiplier. default: 1 type: object required: - api_key title: Sarvam SmallestAISTTConfiguration: properties: provider: type: string const: smallest title: Provider default: smallest api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: Smallest AI STT model. Supports 38 languages with real-time streaming. default: pulse examples: - pulse language: type: string title: Language description: ISO 639-1 language code for transcription. default: en examples: - en - hi - fr - de - es - it - nl - pl - ru - pt - bn - gu - kn - ml - mr - ta - te - pa - or - bg - cs - da - et - fi - hu - lt - lv - mt - ro - sk - sv - uk allow_custom_input: true type: object required: - api_key title: Smallest AI description: Smallest AI ultralow-latency TTS (Waves) and STT (Pulse) APIs. provider_docs_url: https://smallest.ai/docs SmallestAITTSConfiguration: properties: provider: type: string const: smallest title: Provider default: smallest api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: Smallest AI TTS model. lightning_v3.1_pro is the premium pool (American, British, Indian accents); lightning_v3.1 is the standard pool with 217 voices across 12 languages. default: lightning_v3.1 examples: - lightning_v3.1 - lightning_v3.1_pro voice: type: string title: Voice description: "Smallest AI voice ID. Available voices differ by model: lightning_v3.1 has a broad multilingual pool; lightning_v3.1_pro has premium American, British, and Indian accent voices (English + Hindi only)." default: sophia examples: - sophia - avery - liam - lucas - olivia - ryan - freya - william - devansh - arjun - niharika - maya - dhruv - mia - maithili allow_custom_input: true model_options: lightning_v3.1: - sophia - avery - liam - lucas - olivia - ryan - freya - william - devansh - arjun - niharika - maya - dhruv - mia - maithili lightning_v3.1_pro: - meher - rhea - aviraj - cressida - willow - maverick language: type: string title: Language description: ISO 639-1 language code for synthesis. default: en examples: - en - hi - fr - de - es - it - nl - pl - ru - ar - bn - gu - he - kn - mr - ta allow_custom_input: true speed: type: number maximum: 2 minimum: 0.5 title: Speed description: Speech speed multiplier (0.5 to 2.0). default: 1 type: object required: - api_key title: Smallest AI description: Smallest AI ultralow-latency TTS (Waves) and STT (Pulse) APIs. provider_docs_url: https://smallest.ai/docs SpeachesLLMConfiguration: properties: provider: type: string const: speaches title: Provider default: speaches api_key: anyOf: - type: string - items: type: string type: array - type: "null" title: Api Key description: Usually not required for self-hosted endpoints. Leave blank unless your server enforces one. model: type: string title: Model description: Model name as exposed by your OpenAI-compatible server. default: llama3 examples: - llama3 - mistral - phi3 - qwen2 - gemma2 - deepseek-r1 allow_custom_input: true base_url: type: string title: Base Url description: OpenAI-compatible endpoint (Ollama, vLLM, etc.). default: http://localhost:11434/v1 type: object title: Local Models (Speaches) description: Self-hosted OpenAI-compatible local models. See the Speaches project for setup and supported backends. SpeachesSTTConfiguration: properties: provider: type: string const: speaches title: Provider default: speaches api_key: anyOf: - type: string - items: type: string type: array - type: "null" title: Api Key description: Usually not required for self-hosted STT. Leave blank unless enforced. model: type: string title: Model description: Whisper model identifier as served by your STT endpoint. default: Systran/faster-distil-whisper-small.en examples: - Systran/faster-distil-whisper-small.en - Systran/faster-whisper-large-v3 allow_custom_input: true language: type: string title: Language description: ISO 639-1 language code. default: en examples: - en - ar - nl - fr - de - hi - it - pt - es allow_custom_input: true base_url: type: string title: Base Url description: OpenAI-compatible STT endpoint (Speaches, etc.). default: http://localhost:8000/v1 type: object title: Local Models (Speaches) description: Self-hosted OpenAI-compatible local models. See the Speaches project for setup and supported backends. SpeachesTTSConfiguration: properties: provider: type: string const: speaches title: Provider default: speaches api_key: anyOf: - type: string - items: type: string type: array - type: "null" title: Api Key description: Usually not required for self-hosted TTS. Leave blank unless enforced. model: type: string title: Model description: Model name as served by your TTS endpoint (e.g. Kokoro-FastAPI). default: kokoro examples: - hexgrad/Kokoro-82M allow_custom_input: true voice: type: string title: Voice description: Voice ID for the TTS engine. default: af_heart allow_custom_input: true base_url: type: string title: Base Url description: OpenAI-compatible TTS endpoint (Kokoro-FastAPI, etc.). default: http://localhost:8000/v1 speed: type: number maximum: 4 minimum: 0.25 title: Speed description: Speech speed (0.25 to 4.0). default: 1 type: object title: Local Models (Speaches) description: Self-hosted OpenAI-compatible local models. See the Speaches project for setup and supported backends. SpeechmaticsSTTConfiguration: properties: provider: type: string const: speechmatics title: Provider default: speechmatics api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: "Speechmatics operating point: 'standard' or 'enhanced'." default: enhanced language: type: string title: Language description: ISO 639-1 language code. default: en examples: - ar - ar_en - ba - eu - be - bn - bg - yue - ca - hr - cs - da - nl - en - eo - et - fi - fr - gl - de - el - he - hi - hu - id - ia - ga - it - ja - ko - lv - lt - ms - en_ms - mt - cmn - cmn_en - cmn_en_ms_ta - mr - mn - no - fa - pl - pt - ro - ru - sk - sl - es - sw - sv - tl - ta - en_ta - th - tr - uk - ur - ug - vi - cy type: object required: - api_key title: Speechmatics UltravoxRealtimeLLMConfiguration: properties: provider: type: string const: ultravox_realtime title: Provider default: ultravox_realtime api_key: anyOf: - type: string - items: type: string type: array title: Api Key model: type: string title: Model description: Ultravox realtime voice-agent model. default: ultravox-v0.7 examples: - ultravox-v0.7 - fixie-ai/ultravox allow_custom_input: true voice: type: string title: Voice description: Ultravox voice name or voice ID. default: Mark type: object required: - api_key title: Ultravox Realtime ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type input: title: Input ctx: type: object title: Context type: object required: - loc - msg - type title: ValidationError XAITTSConfiguration: properties: provider: type: string const: xai title: Provider default: xai api_key: anyOf: - type: string - items: type: string type: array title: Api Key voice: type: string title: Voice description: xAI voice persona. default: eve examples: - eve - ara - leo - rex - sal allow_custom_input: true language: type: string title: Language description: BCP-47 language code for synthesis (e.g. 'en', 'fr', 'de'), or 'auto' for automatic language detection. default: en allow_custom_input: true type: object required: - api_key title: xAI ````