fish-audio

Fish Audio — Text-to-Speech

Generate narration / voiceover through AceDataCloud's Fish Audio API.

Setup: See authentication for token setup.

Quick Start

curl -X POST https://api.acedata.cloud/fish/tts \
  -H "Authorization: ******ACEDATACLOUD_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "model: s2-pro"

Synchronous responses return a direct audio URL:

Endpoints

Workflows

1. Find a reference voice

The response includes items[] with public voice metadata such as _id, title, languages, tags, visibility, and state. Use an item _id as reference_id in TTS requests.

2. Text-to-Speech

3. One-shot voice cloning

Use a temporary reference voice without creating a persistent model:

audio must be a public HTTPS MP3/WAV URL and text must be the exact transcript. Use one reference lasting 10–270 seconds. Do not combine references with reference_id; use reference_id when the same saved/public voice will be reused. Raw bytes, Base64, data URIs, and MessagePack are not accepted by the AceDataCloud endpoint.

4. Async TTS

Async: See async task polling. Poll via POST /fish/tasks with {"id":"..."}.

Parameters — /fish/tts

Header

JSON body

Gotchas

• The documented TTS endpoint is POST /fish/tts — not /fish/audios.
• Choose the Fish engine with the model request header, not a JSON model field.
• Use reference_id from GET /fish/model — not voice_id.
• Use references for a one-shot clone that is not saved as a model.
• Billing is based on the target text UTF-8 byte count; the reference audio does not add a separate clone fee.
• Synchronous requests return audio_url directly; async jobs should be polled via /fish/tasks.