Clone a Voice

Upload a reference audio file to create a reusable voice_id for later use when generating speech with TTS or TTSD.

1. Create an API Key

   Open the API Key management platform, create an API Key, and save it as an environment variable. Do not write the API Key into client-side code or commit it to a repository.

   MOSS_API_KEY=<your_api_key_here>

2. Prepare the request input

   Prepare a local reference audio file, and enter a voice name and description as needed.

   FieldTypeRequirementDescription

   audio_sample: fileRequired

   A local reference audio file used to clone the voice.

   name: stringOptional

   Voice name.

   description: stringOptional

   Voice description.

   This request uploads multipart/form-data and has no JSON request body. See the complete command in the next step.

3. Send a create request

   Send a request to POST /v1/audio/voices. After creation succeeds, the API returns a voice object.

   curl -X POST "https://api.mosi.cn/v1/audio/voices" \
     -H "Authorization: Bearer $MOSS_API_KEY" \
     -F "audio_sample=@/path/to/sample.wav" \
     -F "name=customer-service-voice"

   import os
   import requests
   
   resp = requests.post(
       "https://api.mosi.cn/v1/audio/voices",
       headers={"Authorization": f"Bearer {os.environ['MOSS_API_KEY']}"},
       files={"audio_sample": open("/path/to/sample.wav", "rb")},
       data={"name": "customer-service-voice"},
   )
   print(resp.json())

   const form = new FormData()
   form.append('audio_sample', audioFile)
   form.append('name', 'customer-service-voice')
   const resp = await fetch('https://api.mosi.cn/v1/audio/voices', {
     method: 'POST',
     headers: { Authorization: `Bearer ${apiKey}` },
     body: form,
   })

4. Read the voice_id

   After creation succeeds, the id in the response is the voice_id you can use for subsequent speech generation.

   {
     "id": "<voice_id>",
     "object": "audio.voice",
     "created_at": 1710000000,
     "name": "customer-service-voice"
   }

5. Verify success

   Success indicator: the response returns a reusable voice_id, which you can reference via voice or voice_id in subsequent TTS / TTSD calls.

Next steps