菜单
Referencia tecnica de Gemini TTS — voces disponibles, audio tags, formato multi-speaker, framework de prompting y limitaciones. Consulta al planificar voiceover o generar audio.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Criterios de calidad para sesiones de auto-mejora — cómo convertir drafts AFP en PRs revisables, cuándo renderizar evidencia y cuándo abstenerse.
Best practices for Remotion - Video creation in React
Drive a full end-to-end test of the video generation platform through the browser. Use this skill whenever testing the Docker Compose stack, verifying a video generation flow, checking the chat UI, debugging pipeline stage transitions, or validating that a fix actually works in the running app. Also use after deploying changes to any of the 3 services (agent, render-service, web) to catch regressions. Even if the user just says "test it" or "does it work?" in the context of the video platform, this is the right skill.
Validate and render a Remotion video from a config.json to MP4. Use this skill when the user wants to render a video, test a config, preview a render, check if a config is valid, or re-render after changes. Trigger on phrases like "render", "renderiza", "genera el video", "prueba el config", or any mention of running the render pipeline locally (not through Docker — that's the agent pipeline). Also use when the user names a specific content slug and wants to see the output.
Identidad visual y editorial de Linea Directa para generacion de videos. Colores, mascota PhoneMascot, tono de marca, tipografia y defaults de composicion. Usala al generar escaletas, escribir copy o tomar decisiones creativas.
Remata configs de vídeo de Remotion con dirección editorial, sincronía entre guion/audio/animación, beats narrativos y timing visual. Úsala después de generar un draft de tutorial o short y antes de renderizar.
| name | gemini-tts |
| description | Referencia tecnica de Gemini TTS — voces disponibles, audio tags, formato multi-speaker, framework de prompting y limitaciones. Consulta al planificar voiceover o generar audio. |
Technical reference for the Gemini TTS model (gemini-3.1-flash-tts-preview).
| Voice | Character | Best for |
|---|---|---|
| Orus | Warm, didactic | Tutorials, explainers |
| Kore | Corporate, professional | Business content |
| Puck | Energetic, young | Social media, shorts |
| Charon | Deep, authoritative | Narration, serious topics |
| Leda | Soft, feminine | Calm, intimate content |
| Zephyr | Neutral, calm | General purpose |
| Aoede | Bright, musical | Creative, upbeat content |
| Fenrir | Bold, dramatic | Impact moments, trailers |
| Achernar | Clear, precise | Technical content |
| Algieba | Warm, resonant | Storytelling |
| Autonoe | Gentle, nurturing | Educational, kids |
| Callirrhoe | Melodic, expressive | Entertainment |
| Despina | Crisp, articulate | News-style delivery |
| Erinome | Smooth, sophisticated | Premium, luxury |
| Gacrux | Gruff, textured | Character voices |
| Iapetus | Steady, reliable | Instructional |
| Keid | Light, airy | Lifestyle content |
| Laomedeia | Rich, commanding | Leadership content |
| Pulcherrima | Elegant, refined | Formal presentations |
| Rasalgethi | Deep, thoughtful | Philosophical content |
| Sadachbia | Friendly, approachable | Conversational |
| Sadaltager | Energetic, motivational | Sports, fitness |
| Schedar | Mature, wise | Documentary style |
| Sulafat | Playful, quirky | Fun, casual content |
| Umbriel | Mysterious, atmospheric | Suspense, sci-fi |
| Vindemiatrix | Confident, assertive | Sales, persuasion |
| Enceladus | Warm, inviting | Welcome messages |
| Thalassa | Serene, flowing | Meditation, relaxation |
| Proteus | Versatile, adaptive | Multi-genre |
| Dione | Bright, cheerful | Celebrations, promos |
Inline modifiers in brackets that control delivery. The TTS engine interprets them as performance directions — no code changes needed, just include them in the text.
[amazed] This is incredible!
[excited] We just launched the new feature!
[sarcastic] Oh great, another meeting.
[tired] It's been a long day...
[whispers] This is a secret.
[cheerful] Welcome to the show!
[serious] Let's talk about security.
[sad] Unfortunately, the project was cancelled.
[laughs] That's hilarious!
[sighs] Here we go again.
[gasp] I can't believe it!
[cough] Excuse me.
[giggles] You're funny.
[very fast] This part needs to be quick!
[very slow] Let... that... sink... in.
[shouting] ATTENTION EVERYONE!
[softly] Just between us...
[like a radio announcer] Coming up next...
[like a sports commentator] And he scores!
[whispers] Este es un secretoUp to 2 speakers per scene. Uses multi_speaker_voice_config API instead of voice_config.
{
"voiceover": {
"enabled": true,
"provider": "gemini",
"language": "es-ES",
"speakers": [
{ "name": "Ana", "voiceId": "Leda" },
{ "name": "Carlos", "voiceId": "Orus" }
],
"scenes": {
"0": "Ana: Bienvenidos al tutorial.\nCarlos: Hoy hablamos de Docker.",
"1": { "text": "Ana: [excited] Veamos el ejemplo.\nCarlos: Abre tu terminal." }
}
}
}
When speakers is present, multi-speaker mode activates. When absent, single-speaker mode uses voiceId.
speakers configFor best quality, structure text with:
For single-speaker, embed guidance via audio tags. For multi-speaker, speaker names provide audio profile context.