Tools · Media
text_to_speech
Can wait for approvalConvert text to spoken audio. Saves an audio file and returns its path so a chat surface can play it. Use for a spoken summary or voice reply.
When to use: Use text_to_speech to turn text into spoken audio — a summary read aloud, a voice reply, a narration. It saves an audio file and returns its path with a MEDIA: tag a chat surface can play. Keep the text natural to hear (short sentences, no markup). Pick a voice if the user asked for one.
Example
The call
{
"tool": "text_to_speech",
"arguments": {
"text": "Your export is ready."
}
}Needs pip install 'shipit-agent[tts]'
So it isn't run here, and no output is shown: nothing on this page is made up.
Parameters
| Name | Type | Description |
|---|---|---|
| text* | string | The text to speak. |
| voice | string | Voice name (optional; backend default otherwise). |
| provider | string | Backend name (optional; auto-selected). |
* required
More in Media
Look at images, and make images, speech and video.