render_voiceover
Convert narration text into local MP3 audio files via OpenRouter speech models, with optional voice cloning and custom output paths for voiceover production.
Instructions
Render narration text to a local audio file via OpenRouter.
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": {
"text": "<text>"
},
"name": "render_voiceover"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | The narration script. Vietnamese diacritics are preserved verbatim. | |
| voice | No | Provider voice id. Leave empty to use the model's default -- Fish Audio documents no preset voice ids, so empty is correct there. | |
| overwrite | No | False (default) never clobbers an existing file -- a numbered sibling is written instead and returned as audio_path. | |
| output_path | No | Absolute or relative destination file (e.g. "D:/campaigns/abc/audio/narration.mp3"). Parent directories are created. Leave empty to write into the configured output directory. | |
| instructions | No | Tone direction. Only forwarded to providers that document it (currently OpenAI); otherwise reported back in "warnings". | |
| reference_text | No | Optional transcript of the reference sample. | |
| response_format | No | "mp3" (default) or "pcm". | |
| reference_audio_path | No | Optional local audio sample for stateless voice cloning on models that support it. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||