Turn text into speech
Reads text aloud in a stock voice and saves the MP3 in the file store with a download link; up to 5,000 characters a call.
$0.07 per 1,000 characters, rounded up
From your agent’s balance. A call that fails costs nothing.
An example
Record a short holiday greeting for the phone line: we're closed from December 24 to 26.
Your agent callsspeech_synthesize$0.07 per 1,000 characters, rounded up
The example business is Halverson Cycle & Repair, a bike shop with a repair workshop in Portland, Oregon. The reply is the one the tool really gives.
{
"text": "Thank you for calling Halverson Cycle & Repair. The shop and the workshop are closed from December 24 to 26. From December 27 we are here again, Monday to Saturday, 10 to 7.",
"voice": "sarah",
"name": "Holiday greeting 2026"
}Use it when
The business needs spoken audio: a phone greeting, a voice note, a short audio guide.
What it does
An MP3 of the text read aloud by one of the voices (speech_list_voices), saved in the file store with a download link. Up to 5,000 characters a call; it reads the language the text is written in. The file carries a machine-readable mark that the speech is AI-generated (ID3: AIGenerated, IPTC digital source type).
What comes back
file: the MP3 with its file_id, size and download link; voice; characters: how many were read. Every reply also carries cost_usd and balance_usd.
Inputs
| Name | Type | What it is |
|---|---|---|
textRequired | string | 1 to 5,000 characters. |
voice | string | A voice from speech_list_voices; the first one when left out. Up to 40 characters. |
name | string | File name for the MP3. Up to 200 characters. |
The call
Over MCP, call speech_synthesize on https://api.conecto.chat/mcp/speech. Over REST:
curl -X POST https://api.conecto.chat/v1/tools/speech_synthesize \
-H "Authorization: Bearer $CONECTO_KEY" \
-H "Content-Type: application/json" \
-d '{"text":"Thank you for calling Halverson Cycle & Repair. The shop and the workshop are closed from December 24 to 26. From December 27 we are here again, Monday to Saturday, 10 to 7.","voice":"sarah","name":"Holiday greeting 2026"}'When it refuses
A refused call costs nothing and says what to do next.
| Code | When | What to do |
|---|---|---|
not_found404 | No stock voice has that name. | Pick one from speech_list_voices. |
storage_full409 | The file store has no room for the MP3. | Delete files with files_delete, or add room with files_add_storage. |
unavailable503 | Speech is not switched on yet, or the speech service failed or did not answer. | Try again later; nothing was charged. |
More Speech tools
All 3 tools- Transcribe audio
speech_transcribeTurns the speech in an audio or video file from the store into text, in about 100 languages, with speakers and timestamps if asked.$0.01 per started minute of audio - List voices
speech_list_voicesThe stock voices text can be read aloud in; each speaks about 30 languages, and the text decides which.Free*
Give this to your agent.
Set up Conecto from https://conecto.chat/SKILL.md