Communitygithub.com

9018/mychat

Genera narración en mandarín y multilingüe con Volcengine Doubao Speech 2.0. Úsalo al crear locuciones en chino, cuando el usuario prefiera Doubao/Volcengine/火山引擎/豆包 TTS, o cuando la narración necesite metadatos de marcas de tiempo a nivel de carácter para subtítulos.

¿Qué es mychat?

Esta habilidad habilita la síntesis de voz (TTS) utilizando la API de Volcengine Doubao Speech 2.0, especializada en narración en mandarín y multilingüe. Proporciona metadatos de sincronización a nivel de palabra (`sentences[].words[]`) ideales para generar subtítulos precisos. La habilidad admite llamadas síncronas y asíncronas (recomendadas para narraciones largas) y requiere configurar las variables de entorno `DOUBAO_SPEECH_API_KEY` y `DOUBAO_SPEECH_VOICE_TYPE`. Incluye un selector TTS y un proveedor directo, permitiendo controlar parámetros como `voice_id`, `speech_rate`, `sample_rate` y `enable_timestamp`. Se recomienda un flujo de trabajo que primero genere una muestra corta para aprobación, evitando ajustes de velocidad que sacrifiquen la naturalidad. La habilidad está diseñada para entornos como Claude Code u otras herramientas de agente de IA que integren la ejecución de herramientas de Python, y maneja la autenticación mediante claves API de la nueva consola.

Compatible con~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/9018/mychat/tree/HEAD/OpenMontage/.agents/skills/doubao-tts

Preguntar en tu IA favorita

Abre un nuevo chat con esta habilidad de agente ya precargada.

Documentación

Doubao TTS

Requiere DOUBAO_SPEECH_API_KEY en .env. Establece DOUBAO_SPEECH_VOICE_TYPE para la voz predeterminada, o pasa voice_id a la herramienta.

API Actual

Usa el flujo de clave API de la nueva consola:

X-Api-Key: ${DOUBAO_SPEECH_API_KEY}
X-Api-Resource-Id: seed-tts-2.0

No uses X-Api-App-Id y X-Api-Access-Key con una clave API de la nueva consola. Si la API devuelve load grant: requested grant not found, probablemente el tipo de clave o el encabezado de autenticación son incorrectos.

Para narración de video larga, prefiere el endpoint asíncrono:

POST https://openspeech.bytedance.com/api/v3/tts/submit
POST https://openspeech.bytedance.com/api/v3/tts/query

Esto devuelve audio_url más los metadatos de sincronización de sentences[].words[] que se pueden usar para crear subtítulos.

Uso en OpenMontage

Genera con el selector TTS:

from tools.audio.tts_selector import TTSSelector

result = TTSSelector().execute({
    "preferred_provider": "doubao",
    "text": "如果 AI 真的会改变未来,普通人到底该怎么参与?",
    "voice_id": "zh_female_vv_uranus_bigtts",
    "output_path": "projects/my-video/assets/audio/narration.mp3",
    "speech_rate": 0,
    "enable_timestamp": True,
})

O llama al proveedor directamente:

from tools.audio.doubao_tts import DoubaoTTS

result = DoubaoTTS().execute({
    "text": "短样本试听文本。",
    "voice_id": "zh_female_vv_uranus_bigtts",
    "output_path": "projects/my-video/assets/audio/doubao_sample.mp3",
})

El proveedor escribe:

  • output_path: archivo de audio descargado
  • metadata_path: JSON completo de la respuesta de la consulta, por defecto <output_path>.json

Flujo de Trabajo Recomendado

  1. Genera una muestra de 10-15 segundos antes de una narración completa de pago.
  2. Pide al usuario que apruebe la naturalidad, el acento y la velocidad de la voz.
  3. Genera la narración completa solo después de la aprobación.
  4. Conserva el JSON de la consulta. Es la fuente de verdad para la sincronización de subtítulos.
  5. Construye los subtítulos a partir de sentences[].words[], no de la estimación de la longitud del texto.
  6. Agrupa los subtítulos por frases semánticas chinas antes de aplicar las marcas de tiempo. No dividas solo por un número fijo de caracteres; puede romper frases como "在不押单个公司的情况下" o "可能会被慢慢稀释" y perjudicar la comprensión.
  7. Deja que la duración del video siga el ritmo de voz aprobado, a menos que el usuario pida explícitamente igualar un tiempo de ejecución anterior.

Parámetros

  • voice_id: speaker / tipo de voz de Doubao. Por defecto DOUBAO_SPEECH_VOICE_TYPE.
  • resource_id: usa seed-tts-2.0 para las voces de Doubao Speech 2.0.
  • speech_rate: 0 es normal, 100 es 2x, -50 es 0.5x.
  • sample_rate: por defecto 24000.
  • enable_timestamp: por defecto true.
  • return_usage: por defecto true, solicita metadatos de uso cuando estén disponibles.

No pases additions.explicit_language por defecto. Algunas combinaciones de endpoint/clave rechazan zh-cn con unsupported additions explicit language zh-cn.

Para explicaciones calmadas en mandarín, empieza con speech_rate: 0. Si el resultado es demasiado largo para el formato aprobado, haz una muestra de comparación breve con speech_rate: 25 o 50 antes de regenerar la narración completa. No aceleres solo para igualar la duración de un proveedor anterior si el usuario prefiere el ritmo natural de Doubao.

Solución de Problemas

  • load grant: requested grant not found: tipo de clave incorrecto o encabezado de autenticación incorrecto. Usa X-Api-Key para las claves API de la nueva consola.
  • speaker permission denied: el id de voz es incorrecto o no está autorizado para el recurso seleccionado.
  • quota exceeded: se superó la cuota, los caracteres de por vida o la concurrencia.
  • Faltan marcas de tiempo: verifica enable_timestamp: true, conserva el JSON de la consulta y confirma que el endpoint seleccionado devolvió sentences.

Seguridad

Nunca imprimas ni escribas la clave API en registros, metadatos, parches o artefactos del proyecto. .env.example debe contener solo nombres de variables vacíos.

Individual skills in this repo

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

9018/mychat

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).

9018/mychat

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.

9018/mychat

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

9018/mychat

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

9018/mychat

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".

9018/mychat

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.

9018/mychat

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

9018/mychat

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.

9018/mychat

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`).

9018/mychat

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.

9018/mychat

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`.

9018/mychat

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.

9018/mychat

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).

9018/mychat

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.

9018/mychat

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.

9018/mychat

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.

9018/mychat

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.

9018/mychat

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

9018/mychat

Three.js animation - keyframe animation, skeletal animation, morph targets, animation mixing. Use when animating objects, playing GLTF animations, creating procedural motion, or blending animations.

9018/mychat

Download video and audio from YouTube and 1000+ sites using yt-dlp. No API keys needed. Use when: (1) Downloading a video from YouTube or other sites, (2) Extracting audio from a video URL, (3) Downloading subtitles/captions from a video, (4) Getting video metadata without downloading.

Skills relacionados