Communitygithub.com

NeverSight/learn-skills.dev

Workflow de recherche méthodique et de mise en œuvre pour les modèles de synthèse vocale (TTS). À utiliser pour rassembler des ressources académiques, localiser les dépôts officiels et communautaires, adapter des architectures à de nouvelles langues, entraîner ou évaluer des systèmes TTS.

Qu'est-ce que learn-skills.dev ?

Ce workflow est conçu pour les chercheurs et les ingénieurs en synthèse vocale qui souhaitent aborder systématiquement la compréhension, l'adaptation et l'évaluation des modèles TTS. Il guide l'utilisateur à travers une séquence structurée : d'abord, une analyse approfondie de l'architecture à partir des publications fondatrices et des paradigmes de modélisation (autoregressif, non-autoregressif, basé sur la diffusion, etc.). Ensuite, il aide à rassembler les ressources académiques et les implémentations, en distinguant les dépôts officiels, les forks communautaires et les adaptations linguistiques. Le workflow couvre également la préparation des données, la phonémisation et les exigences matérielles pour l'entraînement. Enfin, il propose des stratégies d'évaluation objectives (MCD, WER, F0) et subjectives (MOS, MUSHRA). Ce skill est idéal pour être utilisé avec des agents de codage comme Claude Code, Cursor ou Codex, car il intègre des outils pratiques (web_search, paper_search, hub_repo_search) et des documents de référence pour accélérer la recherche.

Compatible avec~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/NeverSight/learn-skills.dev/tree/HEAD/data/skills-md/adrianstanea/acp3-chatterbox/tts-researcher

Demander à votre IA préférée

Ouvre une nouvelle conversation avec cette compétence d'agent déjà préchargée.

Documentation

Chercheur TTS

Un workflow spécialisé pour rassembler des ressources, adapter des architectures et évaluer des modèles de synthèse vocale (Text-to-Speech).

Workflow de recherche méthodique

Lorsqu'il s'agit de rechercher une architecture TTS ou une adaptation linguistique, suivez cette séquence :

1. Analyse approfondie de l'architecture

  • Identifier les articles fondateurs : Trouvez le(s) article(s) principal(s), les éventuels suivis, et le dépôt officiel.
  • Analyser le paradigme du modèle : Déterminez s'il est autorégressif (AR), non-autorégressif (NAR), basé sur la diffusion ou sur l'appariement de flux.
  • Référence : Consultez references/tts-landscape.md pour un guide sur les paradigmes majeurs.

2. Rassemblement des ressources (académiques + implémentations)

  • Sources primaires : Collectez articles, synthèses et rapports de référence qui définissent l'architecture et son évaluation.
  • Dépôts officiels : Localisez le dépôt GitHub original ou appartenant à une organisation, et notez la licence, la dernière mise à jour et l'état de reproductibilité.
  • Dépôts communautaires : Recherchez des forks et des implémentations tierces, en particulier celles adaptées à de nouvelles langues.
  • Rapport des résultats : Fournissez une courte liste des sources les plus crédibles et pertinentes avant de passer à l'étape suivante.

3. Recherche communautaire et d'adaptation

  • Localiser les implémentations personnalisées : Recherchez sur GitHub les forks ou les implémentations non officielles, en particulier celles ciblant différentes langues (par exemple, "MeloTTS-German", "VITS-Spanish").
  • Difficultés techniques : Notez les défis spécifiques à la langue mentionnés dans les discussions communautaires (par exemple, accent de hauteur, langues tonales, phonémiseurs spécifiques).

4. Exigences d'entraînement et d'adaptation

  • Préparation des données : Identifiez le format de jeu de données requis (par exemple, LJSpeech, LibriTTS) et les besoins en transcription.
  • Phonémisation : Vérifiez la disponibilité des phonémiseurs (par exemple, espeak-ng, gruut) pour la langue cible.
  • Matériel : Estimez les besoins en VRAM pour l'entraînement et l'inférence.
  • Référence : Utilisez references/adaptation-checklist.md pour vérifier l'état de préparation.

5. Stratégie d'évaluation

  • Mesures objectives : Planifiez les mesures MCD (Mel Cepstral Distortion), WER (Word Error Rate) et F0 Correlation.
  • Mesures subjectives : Concevez un test MOS (Mean Opinion Score) ou un test MUSHRA si applicable.
  • Référence : Consultez references/evaluation-guide.md pour les définitions des mesures et les outils.

Outils recommandés

  • google_web_search : Pour trouver des articles et dépôts récents.
  • paper_search : Pour la recherche académique approfondie sur Hugging Face Hub.
  • hub_repo_search : Pour trouver des modèles et jeux de données sur Hugging Face.
  • query-docs : Pour les détails d'implémentation technique des bibliothèques (par exemple, torch, transformers).

Individual skills in this repo

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

NeverSight/learn-skills.dev

Use when generating or modifying Remotion video code, creating demo videos, or working with the demo-video/ directory

NeverSight/learn-skills.dev

Create AI avatar and talking head videos via inference.sh CLI. Recommended: P-Video-Avatar (fastest, cheapest, built-in TTS). Also: OmniHuman, Fabric, PixVerse. Audio: Inworld TTS-2 (100+ languages, emotion steering for characters), ElevenLabs, Kokoro. Capabilities: audio-driven avatars, text-to-avatar, lipsync videos, talking head generation, virtual presenters, UGC content. Use for: AI presenters, explainer videos, virtual influencers, dubbing, marketing videos, UGC ads, gaming avatars, NPC dialogue. Triggers: ai avatar, talking head, lipsync, avatar video, virtual presenter, ai spokesperson, audio driven video, heygen alternative, synthesia alternative, talking avatar, lip sync, video avatar, ai presenter, digital human, ugc, ugc video, ugc ad, avatar ugc

NeverSight/learn-skills.dev

Create AI marketing videos for ads, promos, product launches, and brand content. Models: Veo, Seedance, Wan, FLUX for visuals, Kokoro for voiceover. Types: product demos, testimonials, explainers, social ads, brand videos. Use for: Facebook ads, YouTube ads, product launches, brand awareness. Triggers: marketing video, ad video, promo video, commercial, brand video, product video, explainer video, ad creative, video ad, facebook ad video, youtube ad, instagram ad, tiktok ad, promotional video, launch video

NeverSight/learn-skills.dev

Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Capabilities: text-to-video, image-to-video, reference-to-video, video editing, lipsync, avatar animation, video upscaling, foley sound. Use for: social media videos, marketing content, explainer videos, product demos, AI avatars. Triggers: video generation, ai video, text to video, image to video, veo, animate image, video from image, ai animation, video generator, generate video, t2v, i2v, ai video maker, create video with ai, runway alternative, pika alternative, sora alternative, kling alternative, seedance, happyhorse

NeverSight/learn-skills.dev

ElevenLabs automatic dubbing - translate and dub audio/video into 29 languages while preserving speaker voice via inference.sh CLI. Capabilities: auto speaker detection, voice-preserving translation, video dubbing, audio localization. Use for: content localization, video translation, multilingual content, international distribution. Triggers: dubbing, dub video, translate audio, video translation, audio translation, localize content, elevenlabs dubbing, eleven labs dub, multilingual dub, voice translation, auto dub, language dub, content localization

NeverSight/learn-skills.dev

Explainer video production guide: scripting, voiceover, visuals, and assembly. Covers script formulas, pacing rules, scene planning, and multi-tool pipelines. Use for: product demos, how-it-works videos, onboarding videos, social explainers. Triggers: explainer video, how to make explainer, product video, demo video, video production, video script, animated explainer, product demo video, tutorial video, onboarding video, walkthrough video, video pipeline

NeverSight/learn-skills.dev

Still-to-video conversion guide: model selection, motion prompting, and camera movement. Covers Wan 2.5 i2v, Seedance, Fabric, Grok Video with when to use each. Use for: animating images, creating video from stills, adding motion, product animations. Triggers: image to video, i2v, animate image, still to video, add motion to image, image animation, photo to video, animate still, wan i2v, image2video, bring image to life, animate photo, motion from image

NeverSight/learn-skills.dev

Generate talking head avatar videos with Pruna P-Video-Avatar via inference.sh CLI. Turn a portrait image into a realistic speaking video with built-in TTS. 18x faster and 6x cheaper than competitors. Models: P-Video-Avatar, P-Image (for portrait generation). Capabilities: text-to-avatar, audio-driven avatars, 30 voices, 10 languages, 720p/1080p, built-in TTS, dynamic backgrounds, full-body control. Use for: AI presenters, product demos, explainer videos, virtual influencers, marketing, education, multilingual content, UGC, gaming avatars. Triggers: avatar video, talking head, ai avatar, p-video-avatar, pruna avatar, video avatar, ai presenter, digital human, virtual presenter, lipsync, talking avatar, ai spokesperson, heygen alternative, synthesia alternative, veed alternative, fabric alternative, omnihuman alternative

NeverSight/learn-skills.dev

Generate videos with Pruna P-Video and WAN models via inference.sh CLI. Models: P-Video, WAN-T2V, WAN-I2V. Capabilities: text-to-video, image-to-video, audio support, 720p/1080p, fast inference. Pruna optimizes models for speed without quality loss. Triggers: pruna video, p-video, pruna ai video, fast video generation, optimized video, wan t2v, wan i2v, economic video generation, cheap video generation, pruna text to video, pruna image to video

NeverSight/learn-skills.dev

Render videos from React/Remotion component code via inference.sh. Pass TSX code, get MP4. Supports all Remotion APIs: useCurrentFrame, useVideoConfig, spring, interpolate, AbsoluteFill, Sequence. Configurable resolution, FPS, duration, codec. Use for: programmatic video generation, animated graphics, motion design, data-driven videos, React animations to video. Triggers: remotion, render video from code, tsx to video, react video, programmatic video, remotion render, code to video, animated video, motion graphics code, react animation video

NeverSight/learn-skills.dev

Video ad creation with exact platform-specific specs for TikTok, Instagram, YouTube, Facebook, LinkedIn. Covers dimensions, duration limits, AIDA framework, and caption requirements. Use for: video ads, social media ads, paid media creative, video marketing, ad production. Triggers: video ad, social media ad, tiktok ad, instagram ad, youtube ad, facebook ad, linkedin ad, video creative, ad specs, paid media, video marketing, ad production, reels ad, stories ad, pre roll, bumper ad

NeverSight/learn-skills.dev

Best practices and techniques for writing effective AI video generation prompts. Covers: Veo, Seedance, Wan, Grok, Kling, Runway, Pika, Sora prompting strategies. Learn: shot types, camera movements, lighting, pacing, style keywords, negative prompts. Use for: improving video quality, getting consistent results, professional video prompts. Triggers: video prompt, how to prompt video, veo prompts, video generation tips, better ai video, video prompt engineering, video prompt guide, video prompt template, ai video tips, video prompt best practices, video prompt examples, cinematography prompts

NeverSight/learn-skills.dev

YouTube thumbnail design with specific dimensions, contrast rules, and mobile preview optimization. Covers safe zones, text placement, face expression psychology, and A/B testing. Use for: YouTube thumbnails, video cover images, click-through optimization. Triggers: youtube thumbnail, thumbnail design, video thumbnail, click through rate, ctr optimization, youtube cover, video cover image, thumbnail maker, thumbnail tips, youtube design, video preview image

NeverSight/learn-skills.dev

Landing page conversion optimization with layout rules, hero section design, and CTA psychology. Covers above-the-fold formula, social proof placement, mobile design, and F-pattern reading. Use for: startup landing pages, product pages, SaaS marketing, conversion optimization. Triggers: landing page, hero section, above the fold, conversion optimization, landing page design, cta button, hero image, landing page layout, saas landing page, product page design, conversion rate, landing page best practices

NeverSight/learn-skills.dev

Configure and use the hosted YouTube Data MCP end-to-end with minimal user input. Use when users want the agent to verify Node.js and `npx`, configure MCP server config (Windows/macOS, Cursor/Codex/OpenClaw/OpenCode), request API key at setup time, run post-install capability discovery (`tools/list` and `get_patch_notes`), and then strongly recommend helper skill and Python setup for full local document and spreadsheet workflows.

NeverSight/learn-skills.dev

Creates 120fps GPU-accelerated animations with Motion.dev (Framer Motion successor) for React, Next.js, Svelte, and Astro projects. Use when user requests animation, motion, scroll effects, parallax, hero animations, gestures, drag interactions, spring physics, whileHover effects, whileInView animations, animated UI, micro-interactions, page transitions, or layout animations. Generates production TypeScript/JSX code with accessibility (prefers-reduced-motion) and performance validation (≥60fps). Supports entrance animations, gesture interactions (hover/tap/drag), scroll-based reveals, and layout transitions using spring physics and natural timing. Do NOT use for CSS-only transitions (use native CSS), static sites without JavaScript, Vue animations (use motion-v variant instead), or SVG/Canvas complex animations (GSAP better suited).

NeverSight/learn-skills.dev

Static artifact craft skill for self-contained HTML/CSS/JS documents: docs, sheets, dashboards, explainers, slides, tools, and landing pages. Use when the user asks for a durable, openable, shareable web deliverable they'll keep or hand off — a report, a dashboard, a slide deck, a data table, a page. Local folder first, temporary public link via tunnel (localhost.run), optional durable publish to Surge, GitHub Pages, or Cloudflare. Not for quick look renders, inline snippets, or throwaway scratch. Not for SPA frameworks, backend APIs, database apps, or production product UI.

NeverSight/learn-skills.dev

FFmpeg commands for video/audio conversion, trimming, compression, and processing. Use when user mentions "ffmpeg", "convert video", "compress video", "extract audio", "trim video", "gif from video", "video codec", "transcode", "screen recording", "merge videos", "video to mp4", "reduce file size", or any media processing task.

NeverSight/learn-skills.dev

Vim keybindings, motions, text objects, and operators for efficient text editing. Use when user asks about "vim commands", "vim motions", "text objects", "vim keybindings", "vim cheat sheet", "learn vim", "vim in VS Code", or any Vim editing tasks.

NeverSight/learn-skills.dev

Grok Build ONLY. Turn a 2D character still into smooth animation sprites via image_gen/image_edit base → image_to_video (6s/10s run-in-place) → ffmpeg frames → magenta chroma-key → dense sampled sprites (strip/grid/GIF). Use when the user wants video-to-sprite, motion capture from generated video, smoother run/walk cycles from dense frames, or runs /video2dsprite. Do NOT use on Codex/Claude — only Grok Build has image_to_video. Prefer generate2dsprite for crisp pixel sheets without video.

Skills associés