Communitygithub.com

Aseel1600/Edit01

使用 fish.audio 的 S1/S2 语音生成模型创建富有表现力的多语言旁白,并通过 reference_id 复用克隆的语音。当用户偏好 fish.audio / Fish Audio TTS、需要特定游乐场语音模型或需要高情感语音克隆旁白时使用。

Edit01 是什么?

该技能封装了 fish.audio 的文本转语音(TTS)API,支持 S2.1-pro、S2-pro 和 S1 等后端模型,允许开发者通过 HTTP 头选择模型,并通过 reference_id 复用已在 fish.audio 游乐场中创建的克隆语音。其核心功能包括:在 S2 系列模型中嵌入情感标签(如 [laugh]、[whispers])以调节语调;支持 latency(延迟)、normalize(标准化)、prosody(韵律)、mp3_bitrate(比特率)及 temperature(温度)等参数进行质量与延迟的精细调整;采用按 UTF-8 字节计费的定价模式(CJK 及 emoji 字符费用更高)。该技能适用于 OpenMontage 等多个 AI 代理平台,可通过 TTSSelector 或直接调用 FishAudioTTS 提供程序生成旁白。建议的工作流程为先让用户批准 10-15 秒的样本,再进行完整的付费旁白生成,并在原型阶段利用 s2.1-pro-free 的促销免费额度,最终发布时升级为 s2.1-pro。

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/Aseel1600/Edit01/tree/HEAD/.agents/skills/fish-audio-tts

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

fish.audio TTS

需要在 .env 中设置 FISH_AUDIO_API_KEY(可在 https://fish.audio/go-api/api-keys/ 创建)。 在 fish.audio 游乐场中创建语音模型,并将其 ID 作为 reference_id 传入以复用克隆的语音。

当前 API

单次同步调用,返回原始音频字节:

POST https://api.fish.audio/v1/tts
Authorization: Bearer ${FISH_AUDIO_API_KEY}
Content-Type: application/json
model: <backend model>     # HTTP 头选择后端,例如 s1

后端模型通过 model HTTP 头 选择,而不是请求体字段。在 OpenMontage 中,这映射到工具的 model 输入。

后端模型

model 是必需的——没有默认值。请传入以下之一:

  • s2.1-pro — 最新一代。最佳质量:内联情感标签、80+ 语言、多说话人。英雄级旁白。
  • s2.1-pro-free — 促销免费使用 s2.1-pro。仅限推广期内用于草稿、样本和验证运行,费用为 $0。根据 fish.audio 公告:免费至 2026 年 8 月 31 日,受合理使用限制,无 SLA/延迟保证,请求可能被保留,且商业用途受限。切勿将其用于生产或客户旁白。
  • s2-pro — 第一代 S2。稳定高质量,支持情感标签。
  • s1 — 上一代旗舰。为保持与现有集成的兼容性而保留。

计费按输入文本的 UTF-8 字节数(而非字符数)。CJK 文本和 emoji 的成本是相同可见长度 ASCII 字符的 3-4 倍。当前列表定价:s1 / s2-pro / s2.1-pro = 每 1M 字节 $15,s2.1-pro-free = 仅推广期内 $0(该工具的 estimate_cost() 在 2026 年 8 月 31 日之后切换为付费的 s2.1-pro 费率)。大规模批次前请核实当前定价:https://docs.fish.audio/developer-guide/models-pricing/pricing-and-rate-limits。

内联情感标签(仅 S2 模型)

s2-pro / s2.1-pro / s2.1-pro-free 解释嵌入文本中的内联情感标签:

  • 像 [laugh]、[whispers] 这样的标签会在句子中途改变表达方式。
  • 示例:"That's hilarious [laugh] but let me explain seriously."
  • s1 不解释情感标签——它们可能会被当作纯文本朗读,因此针对 s1 时应去除这些标签。

语音选择(reference_id)

  • 在 fish.audio 游乐场中构建或选择一个语音,然后复制其模型 ID。
  • 将其作为 reference_id 传入。当 reference_id 不存在时,选择器的通用 voice_id 可作为别名接受。
  • 如果没有 reference_id,fish.audio 将使用所选模型的默认语音。

此工具不支持即时内联克隆(每次请求上传参考音频+文本)——请先在游乐场中创建语音模型。

OpenMontage 使用

使用 TTS 选择器生成:

from tools.audio.tts_selector import TTSSelector

result = TTSSelector().execute({
    "preferred_provider": "fish_audio",
    "text": "Here's why compound interest quietly beats every get-rich-quick scheme.",
    "model": "s1",
    "reference_id": "<playground voice model id>",
    "output_path": "projects/my-video/assets/audio/narration.mp3",
})

或直接调用提供程序:

from tools.audio.fish_audio_tts import FishAudioTTS

result = FishAudioTTS().execute({
    "text": "Short sample line for approval.",
    "model": "s1",
    "reference_id": "<playground voice model id>",
    "output_path": "projects/my-video/assets/audio/fish_sample.mp3",
})

提供程序将音频写入 output_path,并返回 data.output 以及解析后的 model 和 reference_id。

质量与延迟调优

  • latency:normal(默认,最佳质量)、balanced(稍快)或 low(最快,轻微质量损失)。
  • normalize:默认为 true;保持开启以便数字、日期和货币自然朗读。
  • prosody:可选的 { "speed": 1.0, "volume": 0 } 用于调整语速/音量。
  • mp3_bitrate:128 是一个好的默认值;对于音乐背景较重的混音可提升至 192。
  • temperature:默认为 0.7。调高至 0.9 左右可获得更具表现力的朗读(建议在依赖情感标签时使用);调低可获得更稳定、更可预测的发音。
  • top_p / repetition_penalty:通常保持默认值(0.7 / 1.2)。

推荐工作流程

  1. 在完整的付费旁白生成前,使用所选的 model + reference_id 生成一个 10-15 秒的样本。
  2. 请用户批准语音的自然度、情感和语速。
  3. 仅在批准后生成完整的旁白。
  4. 对于批量/本地化变体(需考虑成本时),在 s2.1-pro-free 上原型开发(推广期内 $0;仅限非商业草稿),最终升级到 s2.1-pro。

故障排除

  • 401 Unauthorized:FISH_AUDIO_API_KEY 错误或缺失。
  • 402 / 付款错误:账户余额不足。
  • 404 / 语音错误:reference_id 错误或不属于该账户。
  • 音频为空/过短:检查 text 是否非空,以及 normalize 是否未去除整个输入。

安全

切勿将 API 密钥打印或写入日志、元数据、补丁或项目工件中。.env.example 应仅包含空的变量名。

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

Aseel1600/Edit01

Generate AI videos from text prompts using multiple provider gateways. Use when: (1) Generating videos from text descriptions, (2) Creating AI-generated video clips for content production, (3) Image-to-video generation with a reference image, (4) Choosing between video generation providers (VEO, Kling, Sora, Runway, Seedance, MiniMax, Gemini Omni). Supports gateways: HeyGen API, fal.ai API, Kling official direct API, and the Gemini API (Gemini Omni Flash).

Aseel1600/Edit01

Create AI avatar videos with precise control over avatars, voices, scripts, scenes, and backgrounds using HeyGen's v2 API. Use when: (1) Choosing a specific avatar and voice for a video, (2) Writing exact scripts for an avatar to speak, (3) Building multi-scene videos with different backgrounds per scene, (4) Creating transparent WebM videos for compositing, (5) Using talking photos as video presenters, (6) Integrating HeyGen avatars with Remotion, (7) Batch video generation with exact specs, (8) Brand-consistent production videos with precise control.

Aseel1600/Edit01

Use p5.js/canvas for local procedural character effects: particles, weather, squash/stretch, walk cycles, and environmental motion.

Aseel1600/Edit01

Review local character animation with schema checks, Playwright browser previews, frame sampling, and FFmpeg/ffprobe final output checks.

Aseel1600/Edit01

Create videos from a text prompt using HeyGen's Video Agent. Use when: (1) Creating a video from a description or idea, (2) Generating explainer, demo, or marketing videos from a prompt, (3) Making a video without specifying exact avatars, voices, or scenes, (4) Quick video prototyping or drafts, (5) One-shot prompt-to-video generation, (6) User says "make me a video" or "create a video about X".

Aseel1600/Edit01

Generate Mandarin and multilingual narration with Volcengine Doubao Speech 2.0. Use when creating Chinese voiceovers, when the user prefers Doubao/Volcengine/火山引擎/豆包 TTS, or when narration needs character-level timestamp metadata for subtitles.

Aseel1600/Edit01

Video and audio processing with FFmpeg. Use for format conversion, resizing, compression, audio extraction, and preparing assets for Remotion. Triggers include converting GIF to MP4, resizing video, extracting audio, compressing files, or any media transformation task.

Aseel1600/Edit01

Use when implementing Disney's 12 animation principles with Framer Motion in React applications

Aseel1600/Edit01

All animation knowledge for HyperFrames — atomic motion rules, multi-phase scene blueprints, scene transitions, broader motion-design techniques, AND the seven runtime adapters (GSAP default, plus Lottie, Three.js, Anime.js, CSS keyframes, Web Animations API, TypeGPU). Use for any motion or animation task: pick 2-4 rules and compose, or load a blueprint, or look up runtime-specific API (e.g. GSAP eases / Lottie player / Three.js mixer). HyperFrames-native: single paused timeline, seek-safe, deterministic.

Aseel1600/Edit01

HyperFrames CLI dev loop. Use when running npx hyperframes init, add, catalog, capture, lint, validate, inspect, layout, snapshot, preview, play, render, publish, lambda, doctor, browser, info, upgrade, skills, compositions, docs, benchmark, telemetry, transcribe, tts, or remove-background, or when troubleshooting the HyperFrames build/render environment. Entry point for AWS Lambda cloud rendering (`hyperframes lambda deploy / render / progress / destroy / policies`).

Aseel1600/Edit01

The HyperFrames composition contract — build one renderable project. Use for composition structure, the `data-*` timing attributes, `class="clip"`, tracks, sub-compositions, variables, framework-owned media playback, deterministic-render rules, and validation. Read before writing composition HTML.

Aseel1600/Edit01

Non-animation creative direction for HyperFrames videos. Use for design spec (frame.md / design.md) handling, palettes, typography, narration, beat planning, audio-reactive visuals, composition patterns, and brand / style decisions. For atomic motion patterns and scene blueprints, use `hyperframes-animation`.

Aseel1600/Edit01

Audio and media assets for HyperFrames compositions, produced by one shared audio engine (`scripts/audio.mjs`) — multi-provider TTS (HeyGen / ElevenLabs / Kokoro local), background music + sound effects (HeyGen audio-library retrieval by default, with local Lyria / MusicGen BGM generation and a bundled SFX library as the no-credential fallback), Whisper transcription, background removal, and caption authoring. Use for voiceover / TTS, BGM, SFX / sound effects, transcription, captions / subtitles / lyrics / karaoke / per-word styling, voice + provider selection, and music-mood prompting.

Aseel1600/Edit01

Install and wire registry blocks and components into HyperFrames compositions. Use when running hyperframes add, installing a block or component, wiring an installed item into index.html, or working with hyperframes.json. Covers the add command, install locations, block sub-composition wiring, component snippet merging, registry discovery, and authoring a new block or component to contribute upstream (idea → scaffold → validate → PR).

Aseel1600/Edit01

Use when the user wants a short, design-led motion graphic where motion is the message: kinetic typography, stat or number count-up, chart/data-viz hit, logo sting, brand lockup, lower-third, callout, social overlay, animated headline/tweet/news item, motion poster, or quick captured-page highlight. Usually under 10s and up to ~30s, with no narration arc, voice-over, or live-action subject. Can render to MP4 or transparent overlay. Not for longer, multi-scene, narrated, or brand-reel pieces (use general-video), narrated website videos (website-to-video), topic explainers (faceless-explainer), product promos (product-launch-video), PR videos (pr-to-video), or captions on existing footage (embedded-captions). When unsure whether it's a quick motion-first piece or a longer / narrated treatment, see /hyperframes.

Aseel1600/Edit01

Use when the user has a music track (an audio file, or a video to pull audio from) and wants a beat-synced HyperFrames video, calm to hard-hitting. The music drives everything: one analyzer reads it once, the orchestrator lays out the frames and fills a per-frame plan, and one sub-agent builds each frame. Typography and templates are the floor — a complete video needs zero assets — but any images or videos the user supplies are cut into the frames on the same beat grid (beat-cut / ken-burns). The genre (lyric video, slideshow, kinetic promo) falls out of the per-frame choices; the pipeline never branches on it.

Aseel1600/Edit01

Best practices for Remotion - Video creation in React

Aseel1600/Edit01

Toolkit-specific Remotion patterns — custom transitions, shared components, and project conventions. For core Remotion framework knowledge (hooks, animations, rendering, etc.), see the `remotion-official` skill.

Aseel1600/Edit01

Port an existing Remotion (React) composition to HyperFrames HTML. Use ONLY when the user explicitly asks to port/convert/migrate/translate a Remotion source. Do NOT use: (a) authoring a new HyperFrames composition; (b) Remotion mentioned in passing; (c) Remotion code shared as reference only; (d) "same video as my Remotion one" without explicit migrate request — treat as fresh build. Doubt → `/general-video`. One-way, Remotion-only: no reverse export (HyperFrames→Remotion or any framework), no non-Remotion source (After Effects, Framer Motion, plain React/CSS) → out of scope, re-create via `/general-video`. Flags unsupported patterns (useState, useEffect, async calculateMetadata, third-party React libs, `@remotion/lambda`) and recommends runtime interop over lossy translation. Unsure whether to port vs. build fresh, or only a passing Remotion mention? → /hyperframes.

Aseel1600/Edit01

Animate SVG character rigs with GSAP, CSS transforms, Remotion frame control, and HyperFrames-compatible browser previews.

相关技能