Voice cloning

​

Endpoint

​

Request parameters

• model string required
  Cloning model. Use stepaudio-2.5-tts to clone a voice for use with StepAudio 2.5 TTS or Realtime.
• text string optional
  Transcript of the source audio file. If omitted, automatic speech recognition is used. For best results, we recommend providing the transcript.
• file_id string required
  File ID of the source audio used for cloning. Obtain the ID via file upload; set purpose to storage. Supported formats: mp3, wav. Audio length should be 5–10 seconds.
• sample_text string optional
  Text (max 50 characters) used to create a preview clip.

​

Response

• id string
  Voice ID for subsequent audio generation.
• object string
  Object type, always audio.voice.
• duplicated boolean
  Indicates the request was duplicated (returned on repeated calls).
• sample_text string
  Text used for the preview audio.
• sample_audio string
  Preview audio in base64 (wav). Convert to a file to play.

​

Example

curl -L 'https://api.stepfun.ai/v1/audio/voices' \
-H 'Content-Type: application/json' \
-H "Authorization: Bearer $STEP_API_KEY" \
-d '{
    "file_id":"file-Ckyl3cV09A",
    "model":"stepaudio-2.5-tts",
    "text":"StepFun intelligence, 10x possibilities for everyone.",
    "sample_text":"Nice weather today"
}'