How to use voices

Find a voice for Text to Speech or AI Cover, and optionally clone, improve, rename or delete your own.

A voice is identified by a voiceId. Text to Speech and AI Cover take a voiceId; Speech to Text, Text to Music and Interpretation do not use voices at all.

Cloning is optional. Start by listing the voices your API key can already use; create a custom voice only if you want your own.

Two kinds of custom voices

Custom voices are created for one feature. The feature field of List voices shows which one.

	TTS voice	Cover voice
Used by	Text to Speech	AI Cover
feature in the voice list	text-to-speech	ai-cover
Create	Create a TTS voice POST /sound_clone/api/v1/voices/tts	Create a Cover voice POST /sound_clone/api/v1/voices/vc
Result	voiceId returned in the response (data.id)	Training is asynchronous: a webhookId is returned, and the result is sent to your callbackUrl as TRAIN_COVER_SPEAKER (Cover callbacks)
Improve	Improve a TTS voice	Improve a Cover voice (result sent as EDIT_COVER_SPEAKER)
Audio files	mp3/wav/m4a, up to 10 MB each, up to 25 files	mp3/wav/m4a, up to 10 MB each, up to 25 files, more than 1 minute of effective voice in total (silence excluded)

The interactive playground on the create and improve pages cannot send file uploads. This is a limitation of the documentation playground, not of the API. Send the multipart/form-data requests from your own code or an HTTP tool, as in the examples below.

Step 1: List the voices you can use

curl --location 'https://api.myvocal.ai/sound_clone/api/v1/voices' \
--header 'accessKey: <your_api_key>'

Each item has an id (use it as voiceId), a name, a type (cloned or designed), a feature (text-to-speech or ai-cover) and a channel (web or api).

• For the Accent TTS model, add ?modelId=myvocal_v3_accent_enhance. That list includes your own compatible voices plus the prebuilt voices available to your API key. It is a selection aid, not a guarantee that a later generation will succeed.
• Generate a cover accepts your custom voice’s id or a premade voice’s id.

If a listed voice fits your use, you can go straight to Text to Speech or AI Cover.

Step 2: Create your own voice (optional)

TTS voice

curl --location 'https://api.myvocal.ai/sound_clone/api/v1/voices/tts' \
--header 'accessKey: <your_api_key>' \
--form 'files=@"xxx/xxx.mp3"' \
--form 'name="111"'

name must not exceed 32 characters. The response returns the new voice’s id:

{
    "code": 1,
    "message": "Success",
    "data": {
        "id": "7812"
    }
}

Use data.id as voiceId in Create speech. To improve the voice later, upload more files with Improve a TTS voice (the 25-file limit includes the files you uploaded when creating it).

Cover voice

You need a public URL that accepts POST requests to receive the result; see Cover callbacks.

curl --location 'https://api.myvocal.ai/sound_clone/api/v1/voices/vc' \
--header 'accessKey: <your_api_key>' \
--form 'files=@"xxx/xxx.mp3"' \
--form 'name="111"' \
--form 'callbackUrl="http://www.google.com"'

The response returns a webhookId immediately:

{
    "code": 1,
    "message": "Success",
    "data": {
        "webhookId": "1701406584rkzy91"
    }
}

When training ends, MyVocal posts a TRAIN_COVER_SPEAKER callback with the same webhookId and a status of SUCCESS or FAILURE. The documented success sample carries the voice id in data.id. To improve a Cover voice, use Improve a Cover voice; its result arrives as an EDIT_COVER_SPEAKER callback.

Step 3: Manage your voices

Task	Endpoint
Rename a voice	Rename a voice PUT /sound_clone/api/v1/voices/rename/{id}
Delete a custom voice	Delete a voice DELETE /sound_clone/api/v1/voices/{id}

Voice design is temporarily unavailable. Voices you created with it earlier are still returned by List voices and still work with Text to Speech; see Voice Design (temporarily unavailable).

Next steps

Text to Speech quickstart

Synthesize speech with your voiceId.

AI Cover quickstart

Create a cover with a Cover voice.