> ## Documentation Index > Fetch the complete documentation index at: https://typecast.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # Instant cloning > Clone a custom voice from a short audio sample and use it like any built-in voice in subsequent text-to-speech calls. Upload a WAV or MP3 file (max 25 MB). The server extracts a speaker embedding and returns a custom voice ID with the `uc_` prefix that can be passed directly to `POST /v1/text-to-speech` (and any other endpoint that accepts a `voice_id`). The original audio is uploaded to S3 in the background after the response is returned. **Limits** - Audio file: max 25 MB. Supported formats: WAV, MP3. - Audio duration: 5 to 150 seconds. - Voice name: 1-30 characters. - Model: `ssfm-v21` or `ssfm-v30`. The cloned voice is bound to this engine model. - Each plan has a maximum number of active custom voices (the `custom_voice_slot`). Use `DELETE /v1/voices/{voice_id}` to free a slot. **Typical flow** 1. `POST /v1/voices/clone` with the sample audio → receive `voice_id` (e.g. `uc_64a1b2...`). 2. `POST /v1/text-to-speech` with `voice_id` set to the cloned ID. 3. `DELETE /v1/voices/{voice_id}` when you no longer need the voice. ## OpenAPI ````yaml /api-reference/openapi.json post /v1/voices/clone openapi: 3.1.0 info: title: Typecast API version: 0.1.2 x-logo: url: https://typecast.ai/_ipx/_/image/logo/tc_logo.webp servers: - url: https://api.typecast.ai description: Production server security: - ApiKeyAuth: [] paths: /v1/voices/clone: post: tags: - Voices summary: Instant cloning description: >- Clone a custom voice from a short audio sample and use it like any built-in voice in subsequent text-to-speech calls. Upload a WAV or MP3 file (max 25 MB). The server extracts a speaker embedding and returns a custom voice ID with the `uc_` prefix that can be passed directly to `POST /v1/text-to-speech` (and any other endpoint that accepts a `voice_id`). The original audio is uploaded to S3 in the background after the response is returned. **Limits** - Audio file: max 25 MB. Supported formats: WAV, MP3. - Audio duration: 5 to 150 seconds. - Voice name: 1-30 characters. - Model: `ssfm-v21` or `ssfm-v30`. The cloned voice is bound to this engine model. - Each plan has a maximum number of active custom voices (the `custom_voice_slot`). Use `DELETE /v1/voices/{voice_id}` to free a slot. **Typical flow** 1. `POST /v1/voices/clone` with the sample audio → receive `voice_id` (e.g. `uc_64a1b2...`). 2. `POST /v1/text-to-speech` with `voice_id` set to the cloned ID. 3. `DELETE /v1/voices/{voice_id}` when you no longer need the voice. operationId: create_voice_clone_v1_voices_clone_post requestBody: content: multipart/form-data: schema: $ref: >- #/components/schemas/Body_create_voice_clone_v1_voices_clone_post type: object required: - file - name - model properties: file: type: string format: binary description: Audio sample. WAV or MP3, max 25 MB, 5-150 seconds. name: type: string minLength: 1 maxLength: 30 description: Voice name (1-30 characters). model: type: string enum: - ssfm-v21 - ssfm-v30 description: Engine model to clone the voice for. required: true responses: '200': description: Successful Response - Custom voice created content: application/json: schema: $ref: '#/components/schemas/CustomVoiceResponse' example: voice_id: uc_64a1b2c3d4e5f6a7b8c9d0e1 name: my-voice model: ssfm-v30 '400': description: >- Bad Request - Invalid audio file, file size, duration, or other validation error content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: file_too_large: summary: File is too large value: detail: File size exceeds maximum limit audio_too_short: summary: Audio is shorter than 5 seconds value: detail: Audio duration is below minimum audio_too_long: summary: Audio is longer than 150 seconds value: detail: Audio duration exceeds maximum audio_unreadable: summary: Audio metadata cannot be read value: detail: Failed to read audio metadata '401': description: Unauthorized - Invalid or missing API key content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: detail: Invalid API key '403': description: Forbidden - Voice cloning is not available on your plan content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: detail: Voice cloning is not available on your plan '422': description: Validation Error - Invalid request parameters content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: detail: Invalid request format '429': description: Too Many Requests - Rate limit or concurrency limit exceeded content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: detail: Too many requests x-codeSamples: - lang: cURL label: cURL source: | curl --request POST \ --url 'https://api.typecast.ai/v1/voices/clone' \ --header 'X-API-KEY: ' \ -F 'file=@sample.wav' \ -F 'name=my-voice' \ -F 'model=ssfm-v30' - lang: Python label: Python (requests) source: > import requests with open("sample.wav", "rb") as f: response = requests.post( "https://api.typecast.ai/v1/voices/clone", headers={"X-API-KEY": ""}, files={"file": ("sample.wav", f, "audio/wav")}, data={"name": "my-voice", "model": "ssfm-v30"}, ) print(response.json()) # {"voice_id": "uc_64a1b2c3d4e5f6a7b8c9d0e1", "name": "my-voice", "model": "ssfm-v30"} components: schemas: Body_create_voice_clone_v1_voices_clone_post: type: object properties: file: type: string title: File description: Audio sample. WAV or MP3, max 25 MB, 5-150 seconds. contentMediaType: application/octet-stream format: binary name: type: string title: Name description: Voice name (1-30 characters). maxLength: 30 minLength: 1 model: $ref: '#/components/schemas/TTSModel' description: Engine model the voice is cloned for (`ssfm-v21` or `ssfm-v30`). allOf: - $ref: '#/components/schemas/TTSModel' required: - file - name - model title: Body_create_voice_clone_v1_voices_clone_post description: Multipart request body for instant cloning. CustomVoiceResponse: type: object properties: voice_id: type: string title: Voice Id description: >- Custom voice identifier with the `uc_` prefix. Use this value as `voice_id` in `POST /v1/text-to-speech` and other endpoints that accept `voice_id`. example: uc_64a1b2c3d4e5f6a7b8c9d0e1 name: type: string title: Name description: Human-readable voice name (1-30 characters). model: type: string title: Model description: Engine model the voice was cloned for (`ssfm-v21` or `ssfm-v30`). allOf: - $ref: '#/components/schemas/TTSModel' required: - voice_id - name - model title: CustomVoiceResponse description: >- Response of `POST /v1/voices/clone` — custom voice metadata returned by instant cloning. ErrorResponse: type: object properties: detail: type: string description: Error message describing the issue required: - detail example: detail: An error occurred processing the request TTSModel: type: string enum: - ssfm-v30 - ssfm-v21 title: TTSModel description: > TTS model version to use for speech synthesis. Different models offer varying capabilities and quality levels. Available models: - **ssfm-v30**: Latest model with improved prosody and additional emotion presets (recommended) - **ssfm-v21**: Stable production model with proven reliability and consistent quality securitySchemes: ApiKeyAuth: type: apiKey in: header name: X-API-KEY description: >- API key for authentication. You can obtain an API key from the Typecast API Console. ````