> ## Documentation Index > Fetch the complete documentation index at: https://heygen-1fa696a7.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Create or Retrain an Audio Voice > Creates a model-backed audio voice from one or more recordings, or retrains an existing professional voice when `voice_id` is supplied. Retraining requires only `voice_id` and source audio and retains the existing voice's ID, name, language, and mode. The voice is `PENDING` and unavailable for inference while either operation runs. Poll `GET /v3/models/audio/voices/{voice_id}` until its status becomes `ACTIVE` or `FAILED`. `Idempotency-Key` is optional; omitting it means repeated creation requests create separate voices. New voices require an unoccupied professional-voice slot. Each purchased slot provides five pooled trainings per monthly billing period, including initial training; failed trainings do not consume the allowance. ## OpenAPI ````yaml /openapi/external-api.json post /v3/models/audio/voices openapi: 3.1.0 info: title: HeyGen External API version: 1.0.0 description: >- HeyGen's external API for programmatic AI video creation. See https://docs.heygen.com for full documentation. contact: name: HeyGen Product Infra url: https://heygen.com servers: - url: https://api.heygen.com description: Production security: - ApiKeyAuth: [] - BearerAuth: [] tags: - name: Video Agent description: Create videos from text prompts using AI - name: Videos description: Create, list, retrieve, and delete videos - name: Templates description: Generate videos from reusable templates by replacing their variables - name: Voices description: Text-to-speech and voice management - name: Audio description: Search the background-music and sound-effects catalog - name: Video Translate description: Translate videos into other languages - name: AI Clipping description: Turn long-form videos into ready-to-share short clips with captions - name: Batches description: Create and track batches of videos. - name: Video Translation Batches description: Create and track batches of video translations. - name: Lipsync Batches description: Create and track batches of lipsyncs. - name: Asset Batches description: Create and track batches of direct-to-S3 asset uploads. - name: User description: Account information and billing - name: API Keys description: Inspect the API key authenticating the current request - name: Avatars description: List and manage avatars and looks - name: Assets description: Upload files for use in video creation - name: Webhooks description: Manage webhook endpoints and events - name: Lipsync description: Dub or replace audio on existing videos - name: Brand description: >- Brand-related resources — brand kits (colors, fonts, logos) and brand glossaries (custom term translations) - name: HyperFrames description: Render HyperFrames composition zips into video — separate from /v3/videos - name: Models description: '' - name: Filler Word Removal description: '' paths: /v3/models/audio/voices: post: tags: - Models summary: Create or Retrain an Audio Voice description: >- Creates a model-backed audio voice from one or more recordings, or retrains an existing professional voice when `voice_id` is supplied. Retraining requires only `voice_id` and source audio and retains the existing voice's ID, name, language, and mode. The voice is `PENDING` and unavailable for inference while either operation runs. Poll `GET /v3/models/audio/voices/{voice_id}` until its status becomes `ACTIVE` or `FAILED`. `Idempotency-Key` is optional; omitting it means repeated creation requests create separate voices. New voices require an unoccupied professional-voice slot. Each purchased slot provides five pooled trainings per monthly billing period, including initial training; failed trainings do not consume the allowance. operationId: createModelAudioVoice parameters: - $ref: '#/components/parameters/IdempotencyKey' requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/CreateModelAudioVoiceRequest' responses: '202': description: Accepted — submission acknowledged; poll for completion. content: application/json: schema: type: object properties: data: $ref: '#/components/schemas/CreateModelAudioVoiceResponse' '400': description: Invalid request parameters content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/StandardAPIError' examples: invalid_audio: summary: Source audio does not satisfy training requirements value: error: code: invalid_parameter message: >- The supplied recordings must contain at least 20 minutes of audio in total. param: audio doc_url: null voice_capacity: summary: All purchased professional-voice slots are occupied value: error: code: resource_limit_reached message: >- No professional voice slots are available. Purchase another slot, or delete a voice after its training finishes. training_allowance: summary: >- The monthly professional-voice training allowance is exhausted value: error: code: resource_limit_reached message: >- The monthly professional voice training allowance is exhausted. Try again in the next billing period or purchase another slot. '401': description: Authentication failed content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/StandardAPIError' example: error: code: unauthorized message: Invalid or expired API key. Verify your x-api-key header. param: null doc_url: null '403': description: Forbidden content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/StandardAPIError' example: error: code: forbidden message: >- The professional voice cloning API is not enabled for this account. param: null doc_url: null '404': description: Resource not found content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/StandardAPIError' example: error: code: voice_not_found message: Voice not found. param: null doc_url: null '409': description: >- Conflict — either the request conflicts with existing state, or a prior request with this `Idempotency-Key` is still in progress (`request_in_progress`). content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/StandardAPIError' examples: conflict: summary: Resource conflict value: error: code: resource_not_ready message: >- The professional voice must be ACTIVE and have no training in progress before it can be retrained. param: null doc_url: null request_in_progress: summary: Concurrent retry with same Idempotency-Key value: error: code: request_in_progress message: >- A request with this Idempotency-Key is already in progress. Retry shortly. param: null doc_url: null '429': description: Rate limit exceeded content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/StandardAPIError' example: error: code: rate_limit_exceeded message: >- Too many requests. Retry after the duration specified in the Retry-After header. param: null doc_url: null headers: Retry-After: description: Seconds to wait before retrying schema: type: integer '503': description: >- Temporarily unavailable — the request did not complete and is safe to retry. content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/StandardAPIError' example: error: code: service_unavailable message: >- Professional voice source audio ingestion is temporarily unavailable. Retry with the same Idempotency-Key. param: null doc_url: null security: - ApiKeyAuth: [] - BearerAuth: [] components: parameters: IdempotencyKey: name: Idempotency-Key in: header required: false description: >- Optional client-supplied key for safely retrying mutations. Subsequent calls within 24 hours that share this key replay the original response — even if the request body differs slightly (a warning is logged). A retry that arrives while the original is still in flight gets a 409 `request_in_progress`. Keys must be 1–255 characters from `[A-Za-z0-9_:.-]`; a UUID is a safe default. Scope is per-endpoint and per-resource: the same key on a different route or path parameter is independent. schema: type: string pattern: ^[A-Za-z0-9_\-:.]{1,255}$ maxLength: 255 minLength: 1 example: 550e8400-e29b-41d4-a716-446655440000 schemas: CreateModelAudioVoiceRequest: additionalProperties: false description: Create or retrain one model-backed audio voice. properties: mode: anyOf: - $ref: '#/components/schemas/ModelAudioVoiceMode' - type: 'null' default: null description: >- Voice operation mode for a new voice. Ignored when `voice_id` is supplied; the existing mode is retained. Currently only `professional` is supported. voice_id: anyOf: - maxLength: 64 minLength: 1 pattern: ^\S+$ type: string - type: 'null' default: null description: Existing professional voice to retrain. Omit to create a new voice. title: Voice Id name: anyOf: - maxLength: 256 minLength: 1 type: string - type: 'null' default: null description: >- Display name for a new voice. Ignored when `voice_id` is supplied; the existing name is retained. title: Name language: anyOf: - maxLength: 32 minLength: 1 type: string - type: 'null' default: null description: >- Primary language code, such as `en`, for a new voice. Ignored when `voice_id` is supplied; the existing language is retained. title: Language audio: description: >- Source recordings of the same speaker. Each item may be a public HTTPS URL, a HeyGen asset ID, or base64-encoded audio. The recordings must contain at least 20 minutes of audio and no more than 1.5 GB (1,500,000,000 bytes) in total. items: discriminator: mapping: asset_id: $ref: '#/components/schemas/AssetId' base64: $ref: '#/components/schemas/AssetBase64' url: $ref: '#/components/schemas/AssetUrl' propertyName: type oneOf: - $ref: '#/components/schemas/AssetUrl' - $ref: '#/components/schemas/AssetId' - $ref: '#/components/schemas/AssetBase64' maxItems: 10 minItems: 1 title: Audio type: array required: - audio title: CreateModelAudioVoiceRequest type: object CreateModelAudioVoiceResponse: additionalProperties: false description: Identifier returned after voice creation or retraining is accepted. properties: voice_id: description: >- Stable identifier to use when retrieving the voice and its training status. title: Voice Id type: string required: - voice_id title: CreateModelAudioVoiceResponse type: object StandardAPIError: type: object properties: code: type: string description: Machine-readable error code example: invalid_parameter message: type: string description: Human-readable error message example: Video not found param: type: - string - 'null' description: Which request field caused the error doc_url: type: - string - 'null' description: Link to error documentation errors: type: array description: >- Per-item error details for batch/multi-node failures (e.g. graph compilation errors by node). items: $ref: '#/components/schemas/StandardAPIErrorDetail' required: - code - message ModelAudioVoiceMode: description: Supported audio-voice creation implementations. enum: - professional title: ModelAudioVoiceMode type: string AssetId: additionalProperties: false description: Asset input via HeyGen asset ID from the asset upload endpoint. properties: type: const: asset_id description: Input type discriminator title: Type type: string asset_id: description: HeyGen asset ID from the asset upload endpoint title: Asset Id type: string required: - type - asset_id title: AssetId type: object AssetBase64: additionalProperties: false description: Asset input via base64-encoded content. properties: type: const: base64 description: Input type discriminator title: Type type: string media_type: description: MIME type of the encoded content (e.g. "image/png") title: Media Type type: string data: description: Base64-encoded file content title: Data type: string required: - type - media_type - data title: AssetBase64 type: object x-mcp-visible: false AssetUrl: additionalProperties: false description: Asset input via publicly accessible HTTPS URL. properties: type: const: url description: Input type discriminator title: Type type: string url: description: Publicly accessible HTTPS URL for the asset title: Url type: string required: - type - url title: AssetUrl type: object StandardAPIErrorDetail: type: object properties: code: type: string description: Machine-readable error code example: unknown_node_type message: type: string description: Human-readable error message example: Unknown node type node_id: type: string description: Graph node id this error pertains to, if applicable port: type: string description: Port name on the node this error pertains to, if applicable path: type: string description: Field path within the item this error pertains to, if applicable required: - code - message securitySchemes: ApiKeyAuth: type: apiKey in: header name: x-api-key description: HeyGen API key. Obtain from your HeyGen dashboard. BearerAuth: type: http scheme: bearer description: OAuth2 bearer token. ````