Create an audio clip (speech from text, or upload a recording)
create_audio_clipGenerates the audio track a video model needs from text plus a chosen or cloned voice, or from an uploaded recording, and returns a clip id to poll for completion.
Instructions
The soundtrack every video model takes as input. Either text (up to 2000 characters) plus exactly one voice (voice_id from list_voices, or voice_user_id for a cloned voice), or file_path to upload a local WAV/MP3/M4A recording. Returns the clip id; it is ready when wait_for_job(model='audio-clip') reports done (usually seconds). Longer scripts: create several clips and pass all ids to create_craftstory2_video in order.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "create_audio_clip"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| text | No | Script to synthesize (<= 2000 chars) | |
| voice_id | No | Library voice id (from list_voices) | |
| file_path | No | Local path of a recording to upload instead of text | |
| voice_user_id | No | Cloned voice id (from list_voices with include_cloned) |