> ## Documentation Index > Fetch the complete documentation index at: https://anam.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # create voice > Create a voice by cloning from audio or importing an existing provider voice. Send clone audio inline as multipart/form-data (the whole request must stay under ~4.5MB), or first upload a larger clip via `POST /v1/voices/presigned-upload` and reference its `audioKey`. Provider imports are checked against Anam's supported model registry. Cartesia, ElevenLabs, and Fish Audio imports must successfully generate a sample before the voice is persisted; the first import of an ElevenLabs Voice Library voice typically takes about a minute while ElevenLabs adds it to Anam's account. New integrations should prefer POST /v1/voice-imports for synchronous validation and preview generation. An import by provider voice ID shares that endpoint's organization limit: 30 voice imports and model changes an hour, at most 3 at once, refused with 429 `rate_limited` and `Retry-After` before any provider work. ## OpenAPI ````yaml https://api.anam.ai/swagger.json post /v1/voices openapi: 3.1.0 info: title: Anam AI API version: '1.0' servers: - url: https://api.anam.ai description: Anam API security: - BearerAuth: [] tags: - name: Sessions - name: Avatar Videos - name: Meetings - name: Personas - name: Avatars - name: Voices - name: Pronunciation Dictionaries - name: LLMs - name: Knowledge - name: Tools - name: Share Links - name: Engine paths: /v1/voices: post: tags: - Voices summary: create voice description: >- Create a voice by cloning from audio or importing an existing provider voice. Send clone audio inline as multipart/form-data (the whole request must stay under ~4.5MB), or first upload a larger clip via `POST /v1/voices/presigned-upload` and reference its `audioKey`. Provider imports are checked against Anam's supported model registry. Cartesia, ElevenLabs, and Fish Audio imports must successfully generate a sample before the voice is persisted; the first import of an ElevenLabs Voice Library voice typically takes about a minute while ElevenLabs adds it to Anam's account. New integrations should prefer POST /v1/voice-imports for synchronous validation and preview generation. An import by provider voice ID shares that endpoint's organization limit: 30 voice imports and model changes an hour, at most 3 at once, refused with 429 `rate_limited` and `Retry-After` before any provider work. operationId: createVoice requestBody: description: Audio clone data or an existing provider voice to import. required: true content: multipart/form-data: schema: type: object required: - name - audioFile properties: name: type: string description: Display name for the cloned voice audioFile: type: string format: binary description: Audio file to clone the voice from description: type: string description: Optional description of the voice language: type: string default: en description: Language code for the voice enhance: type: boolean default: true deprecated: true description: >- Accepted for compatibility; no longer forwarded to the current Cartesia cloning API. application/json: schema: oneOf: - type: object title: Clone from uploaded audio required: - name - audioKey properties: name: type: string description: Display name for the cloned voice audioKey: type: string description: >- Storage key returned by POST /v1/voices/presigned-upload, after the audio has been uploaded to the presigned URL. Use this for clips larger than ~4.5MB. description: type: string description: Optional description of the voice language: type: string default: en description: Language code for the voice enhance: type: boolean default: true deprecated: true description: >- Accepted for compatibility; no longer forwarded to the current Cartesia cloning API. - type: object title: Import provider voice required: - displayName - provider - providerVoiceId properties: displayName: type: string description: Display name for the imported voice provider: type: string enum: - CARTESIA - ELEVENLABS - FISH_AUDIO providerVoiceId: type: string description: Voice ID in the selected provider providerModelId: type: string enum: - sonic-3.6 - sonic-3.6-2026-08-27 - sonic-3.5 - sonic-3.5-2026-05-04 - sonic-3 - sonic-3-2026-01-12 - sonic-2 - sonic-latest - eleven_v4_turbo - eleven_v3_conversational - eleven_v4 - eleven_v3 - eleven_flash_v2_5 - eleven_multilingual_v2 - eleven_flash_v2 - eleven_turbo_v2_5 - s2.1-pro - s2-pro - s1 description: >- Supported model for the selected provider. Omit to use that provider's default. providerConfig: type: object additionalProperties: true sampleUrl: type: string format: uri description: Optional provider-hosted sample URL retained as metadata isClone: type: boolean description: Legacy compatibility flag gender: type: string enum: - MALE - FEMALE - NEUTRAL country: type: string minLength: 2 maxLength: 2 description: ISO 3166-1 alpha-2 country code description: type: string examples: cloneFromUpload: value: name: My cloned voice audioKey: voice-clones/org_123/sample.wav language: en enhance: true importProviderVoice: value: displayName: My Cartesia voice provider: CARTESIA providerVoiceId: voice_abc123 providerModelId: sonic-3.6 responses: '201': description: Successfully cloned or imported a voice content: application/json: schema: $ref: '#/components/schemas/Voice' examples: default: $ref: '#/components/examples/VoiceResponse' '400': description: >- Bad request - Invalid voice data, unsupported model, or provider validation failed '401': description: Unauthorized - Invalid or missing API key '403': description: >- Forbidden - Requires enterprise plan or API key lacks the required permission '409': description: >- ElevenLabs attachment conflict (`voice_bound_elsewhere`) or another attachment is running (`import_in_progress`, retryable). content: application/json: schema: type: object required: - error - code properties: error: type: string code: type: string enum: - voice_bound_elsewhere - import_in_progress retryable: type: boolean examples: voiceBoundElsewhere: value: error: >- This ElevenLabs voice is linked to another organization. Contact support to use it. code: voice_bound_elsewhere importInProgress: value: error: This ElevenLabs voice is being imported. Retry shortly. code: import_in_progress retryable: true '422': description: >- The voice provider refused to clone from this audio or these parameters. `code` says why: `audio_too_large`, `audio_silent`, `audio_too_short`, or `clone_rejected` for any other refusal, such as an unsupported `language`. Fix the request before retrying. content: application/json: schema: type: object required: - error - code properties: error: type: string code: type: string enum: - audio_too_large - audio_silent - audio_too_short - clone_rejected examples: audioTooShort: value: error: >- The audio is too short to clone. Send 10–15 seconds of the voice speaking. code: audio_too_short '429': description: >- A clone or an import by provider voice ID found the organization's 30 voice clones, imports and model changes this hour spent or 3 running (`code: rate_limited`, `retryable: true`; nothing was sent to the provider), or the voice provider rate limited the validation request. Retry later. headers: Retry-After: description: >- Seconds until the organization's limit allows another clone or import, when it refused the request. schema: type: integer minimum: 1 content: application/json: schema: type: object required: - error properties: error: type: string code: type: string enum: - rate_limited retryable: type: boolean '500': description: Server error '502': description: >- Voice provider or preview storage is temporarily unavailable. A clone answers with `code: provider_unavailable` and `retryable: true`. An uploaded `audioKey` is kept, so the same request can be retried until the upload is 24 hours old; after that, upload the clip again. '503': description: >- The API key could not be checked because of a temporary server problem (the key may be valid), or a clone or an import by provider voice ID found the organization's voice limit couldn't be checked (`code: service_unavailable`, `retryable: true`; nothing was sent to the provider). Retry after `Retry-After` seconds. headers: Retry-After: description: Seconds to wait before retrying. schema: type: integer content: application/json: schema: oneOf: - $ref: '#/components/schemas/ServiceUnavailableError' - type: object required: - error - code properties: error: type: string code: type: string enum: - service_unavailable retryable: type: boolean '504': description: Voice provider validation timed out components: schemas: Voice: type: object description: A voice preset a persona can use for text-to-speech. properties: id: type: string format: uuid description: Unique identifier for the voice. displayName: type: string description: Human-readable name shown in the Lab. provider: type: string enum: - CARTESIA - ELEVENLABS - FISH_AUDIO description: Upstream TTS provider for this voice. providerVoiceId: type: - string - 'null' description: The upstream provider's identifier for the voice. providerModelId: type: - string - 'null' description: The upstream provider's model identifier used to generate speech. sampleUrl: type: - string - 'null' format: uri description: URL of a short audio preview of the voice. previewSampleUrl: type: - string - 'null' format: uri description: Alias for `sampleUrl`, kept for backwards compatibility. gender: type: - string - 'null' enum: - MALE - FEMALE - NEUTRAL - null description: Perceived gender of the voice, if categorised. country: type: - string - 'null' description: ISO 3166-1 alpha-2 country code representing the voice's accent. description: type: - string - 'null' description: Free-form description of the voice's character. displayTags: type: array items: type: string description: Tags used to categorise the voice in the Lab UI. isZdr: type: boolean description: Whether this voice meets the Zero Data Retention requirements. createdByOrganizationId: type: - string - 'null' description: >- ID of the organization that created the voice, or `null` for stock voices. IDs may be either UUIDs or nanoid-style strings depending on when the organization was created. createdAt: type: string format: date-time description: Timestamp when the voice was created. updatedAt: type: string format: date-time description: Timestamp when the voice was last updated. ServiceUnavailableError: type: object required: - error - message properties: error: type: string example: Service temporarily unavailable message: type: string example: We could not check your API key. Please retry shortly. examples: VoiceResponse: summary: A single voice resource value: id: de23e340-1416-4dd8-977d-065a7ca11697 displayName: Lucy - Fresh & Casual provider: ELEVENLABS providerVoiceId: lcMyyd2HUfFzxdCaC4Ta providerModelId: eleven_flash_v2_5 sampleUrl: >- https://newgxnc1uqs0jnqm.public.blob.vercel-storage.com/voice-samples/de23e340-1416-4dd8-977d-065a7ca11697/1760617899390.mp3 previewSampleUrl: >- https://newgxnc1uqs0jnqm.public.blob.vercel-storage.com/voice-samples/de23e340-1416-4dd8-977d-065a7ca11697/1760617899390.mp3 gender: FEMALE country: GB description: >- Energetic and youthful British voice, perfect for narrations and conversational agents. displayTags: - fast isZdr: true createdByOrganizationId: null createdAt: '2026-04-20T10:00:00.000Z' updatedAt: '2026-04-20T10:00:00.000Z' securitySchemes: BearerAuth: type: http scheme: bearer ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.