voice_cover
COSTS CREDITS (see list_song_tools): state the price and get the user's confirmation first. Priced per minute of the source. Re-sing a song with another voice (list_voices), keeping the music. Returns an id; poll get_process_result with action "voice_cover".
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"id": "<id>",
"idempotencyKey": "<idempotencyKey>"
},
"name": "voice_cover"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Source song id (songs[].id from get_generation / list_songs / save_upload). | |
| voice | No | Built-in voice id from list_voices.builtIn. | |
| pitchShift | No | no-change | |
| outputFormat | No | mp3 | |
| voiceModelId | No | Or one of the user's own voices from list_voices.custom. | |
| idempotencyKey | Yes | 8-64 chars [A-Za-z0-9._:-]. Same rules as generate_music: stable per logical request, resend the same key + params after a timeout instead of paying twice; new key when anything changes. |