Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/waker240/FullVideoProductionSkillnpx agentmods add skills/waker240/fullvideoproductionskill/fish-audio-apiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/waker240/fullvideoproductionskill/fish-audio-api)<a href="https://agentmods.dev/skills/waker240/fullvideoproductionskill/fish-audio-api"><img src="https://agentmods.dev/badge/skills/waker240/fullvideoproductionskill/fish-audio-api/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/waker240/fullvideoproductionskill/fish-audio-api"><img src="https://agentmods.dev/badge/skills/waker240/fullvideoproductionskill/fish-audio-api.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00050 | $0.00953 |
| Opus 5.5 | $0.00020 | $0.00381 |
| Sonnet 5.5 | $0.00010 | $0.00191 |
| Haiku 4.5 | $0.00005 | $0.00095 |
Grade A, and why
fish-audio-api scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 20d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fish Audio public API
Use this skill when a video needs Fish narration. The release uses the official POST https://api.fish.audio/v1/tts endpoint. It does not ship a web-session proxy, cookies, an account, or a voice. Node.js 22.20 or later is required. Install FFmpeg/ffprobe for the video audio pipeline.
Configure locally
Copy env.example to the video project's .env, ensure .env is ignored by Git, then fill it locally. Never request that users paste credentials into chat. Existing process environment values take precedence over .env. Scripts never print secret values or upstream error bodies.
| Variable | Meaning |
|---|---|
FISH_API_KEY |
API key created in the user's Fish account; required for generation. |
FISH_REFERENCE_ID |
A voice ID the user has permission to use; required unless a project explicitly supplies one. |
FISH_MODEL |
Defaults to s2.1-pro-free; supported choices also include s1, s2-pro, s2.1-pro. Account access and quotas are provider-controlled. |
No silent model fallback is allowed. An unknown model fails locally, because the provider may otherwise choose a paid default. Availability and pricing can change; check the account before generation. Setting a key does not itself authorize a charge: run synthesis only for the user's requested scope.
Generate and revise
For a scaffolded HyperFrames project, edit scripts/narration.json. Its voice.referenceId and voice.model may be null to use the environment. All other voice settings are explicit in the template. Preview one short paragraph before producing a whole narration.
node scripts/tts-fish.mjs --section s0
node scripts/tts-fish.mjs
node scripts/tts-fish.mjs --section s2 --para 1 --force
--para requires every unselected paragraph in that section to exist. To start a new project, first generate one short section with --section s0; use --para for a later repair. Matching paragraph text and voice profiles reuse frozen audio. --force makes another API request for the selected speech.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 20d ago First seen · 52 lines · 50 tokens per session scan A 0d500be22b52
fish-audio-api is a skill published in the GitHub repository waker240/FullVideoProductionSkill (205 stars, last pushed 20d ago), licensed Apache-2.0. It adds 50 tokens to every session and 953 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-27.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…