Fish audio

Skill AceDataCloud/Skills/skills/fish-audio

Agent Skills for AceDataCloud AI services — music, image, video generation, web search, and more. Compatible with Claude Code, GitHub Copilot, Gemini CLI, and all agentskills.io-compatible agents.

Install

npx -y skills add AceDataCloud/Skills --skill fish-audio

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
13 stars13 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Generate AI text-to-speech audio with Fish Audio and browse public reference voices via AceDataCloud API. Use when creating voiceover/narration audio (TTS), synthesizing multilingual speech, or selecting a Fish reference voice from the model catalog.

The file declares its own license as Apache-2.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

3.8 KB, 968 tokens by cl100k_base, as published. Nobody here has run it

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" \
  -d '{"text":"你好，欢迎使用 AceData Cloud。","reference_id":"d7900c21663f485ab63ebdb7e5905036","format":"mp3"}'

Synchronous responses return a direct audio URL:

{"audio_url":"https://platform.r2.fish.audio/task/8a72ff9840234006a9f74cb2fa04f978.mp3"}

Endpoints

Endpoint	Purpose
`POST /fish/tts`	Text-to-speech generation
`GET /fish/model`	Browse/search public Fish reference voices
`POST /fish/tasks`	Poll async TTS jobs when `async: true`

Workflows

1. Find a reference voice

curl "https://api.acedata.cloud/fish/model?page_size=10&page_number=1&title=Marcus" \
  -H "Authorization: ******ACEDATACLOUD_API_TOKEN"

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

POST /fish/tts
Headers:
  model: s2-pro

{
  "text": "Your narration text.",
  "reference_id": "d7900c21663f485ab63ebdb7e5905036",
  "format": "mp3"
}

3. Async TTS

POST /fish/tts
Headers:
  model: s1

{
  "text": "Longer narration for background processing.",
  "async": true,
  "callback_url": "https://api.acedata.cloud/health"
}

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

Parameters — `/fish/tts`

Header

Parameter	Values	Description
`model`	`"s1"`, `"s2-pro"`	Fish TTS engine selection

JSON body

Parameter	Type / Values	Description
`text`	string	Text to synthesize (required)
`reference_id`	string	Public/reference voice ID from `GET /fish/model`
`format`	`"mp3"`, `"wav"`, `"pcm"`, `"opus"`	Output format
`sample_rate`	integer	Optional output sample rate
`mp3_bitrate`	`64`, `128`, `192`	MP3 bitrate
`opus_bitrate`	integer	Opus bitrate
`latency`	`"normal"`, `"balanced"`	TTS latency mode
`chunk_length` / `min_chunk_length`	integer	Chunking controls
`temperature`, `top_p`, `repetition_penalty`	number	Sampling controls
`max_new_tokens`	integer	Maximum generated tokens
`normalize`	boolean	Normalize generated audio
`prosody`	object	Prosody tuning
`references`	array	Additional reference objects
`callback_url`	string	Async callback URL
`async`	boolean	Run asynchronously and poll `/fish/tasks`

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.
Synchronous requests return audio_url directly; async jobs should be polled via /fish/tasks.
The current OpenAPI spec documents voice browsing via GET /fish/model; it does not document a voice-cloning write endpoint.

Gives 0 of the 12 instructions most video audio skills give in 968 tokens

Counted across 621 of the 795 authors here whose files we hold, read 2026-08-06

read individual rule files for detailed explanationsin 21 of 621, across 9 files
Use WAV PCM 16kHz mono audio formatin 13 of 621, across 4 files
render final videoin 13 of 621, across 6 files
use this skill when dealing with Remotion codein 11 of 621, across 4 files
save generated audio to a WAV filein 11 of 621, across 4 files
handle conversion errors gracefullyin 10 of 621, across 6 files
add captions to videos alwaysin 10 of 621, across 4 files
generate music from text descriptions using MusicGenin 9 of 621, across 2 files
do not skip pipeline layersin 9 of 621, across 3 files
do not make one tool do everythingin 9 of 621, across 3 files
never ask the user to paste their full API keyin 9 of 621, across 3 files
use azure document intelligence for complex pdfsin 9 of 621, across 4 files

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.