Fish Audio S2 Pro
fish_audio/s2-proTurn text into spoken audio, in a saved or cloned voice.
- byte
- $0.00003
- Fish Audio
- 5 min
Overview
Converts text into speech using either a saved voice referenced by id or a voice cloned on the fly from reference audio and its transcript. This is the higher tier, at the same price per byte as the standard one. Output encoding is selectable across compressed and uncompressed containers with bitrate control. A latency mode trades time-to-first-audio against quality, and a chunk length governs how the text is segmented for synthesis, which keeps prosody consistent across long passages. Text normalisation expands numbers, dates, and abbreviations into the way they are spoken.
The audio, returned inline with its media type and size in bytes. Billing counts the bytes of text submitted.
Input
These go in the input object of the run request.
| Field | Type | Required | Description |
|---|---|---|---|
| text | string | Yes | What to say. |
| reference_id | string | No | The id of a saved voice to speak with. |
| format | string | No | Audio container to return. |
| mp3_bitrate | integer | No | Bitrate when returning MP3. |
| chunk_length | integer | No | How much text to synthesise at a time. |
| latency | string | No | Trade responsiveness against quality. |
| normalize | boolean | No | Expand numbers, dates, and abbreviations before speaking them. |
Requests up to 1 MB, text up to 100,000 characters.
Example
A call that works, with your own key.
curl https://gateway.agentsky.dev/v1/run \
-H "authorization: Bearer $AGENTSKY_API_KEY" \
-H "content-type: application/json" \
-d '{"provider":"fish_audio","endpoint":"s2-pro","input":{"text":"Hello, and welcome back to the show.","format":"mp3","mp3_bitrate":128,"latency":"normal"}}'Pricing
$0.00003 per byte on the default plan. Every run carries its price in the response.