synthesize_speech
Converts text to speech audio using a specified voice ID and model, enabling voice output for applications.
Instructions
Synthesize speech. Supply a voice ID supported by the chosen model; none is guessed.
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>",
"voice": "<voice>"
},
"name": "synthesize_speech"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | ||
| model | No | qwen-audio-3.0-tts-flash | |
| voice | Yes | ||
| format | No | ||
| instruction | No | ||
| sample_rate | No |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||