Stats
Actions
Tags
From ravi-system
Gera áudio (TTS) via ElevenLabs. Use quando o usuário quiser: - Converter texto em fala - Gerar áudio narrado - Enviar mensagem de voz gerada - Criar podcast/narração
How this skill is triggered — by the user, by Claude, or both
Slash command
/ravi-system:audioThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Gera áudio a partir de texto usando ElevenLabs Text-to-Speech.
Gera áudio a partir de texto usando ElevenLabs Text-to-Speech.
ravi audio generate "Olá, eu sou o Ravi!"
ravi audio generate "Hello world" --voice JBFqnCBsd6RMkjVDRZzb
ravi audio generate "Texto rápido" --speed 1.5
ravi audio generate "Bom dia a todos" --lang pt
ravi audio generate "Mensagem de voz" --send
ravi audio generate "Conteúdo importante" --send --caption "Escuta isso"
ravi audio generate "Quick response" --model eleven_turbo_v2_5
ravi audio generate "Narração" -o /tmp/audios
| Flag | Descrição | Default |
|---|---|---|
--voice <id> | Voice ID do ElevenLabs | env ELEVENLABS_VOICE_ID ou default |
--model <model> | eleven_multilingual_v2, eleven_turbo_v2_5 | eleven_multilingual_v2 |
--speed <speed> | Velocidade 0.5-2.0 | 1.0 |
--lang <code> | Idioma ISO 639-1 (pt, en, es) | auto-detect |
--format <fmt> | mp3_44100_128, mp3_22050_32, pcm_16000 | mp3_44100_128 |
-o, --output <dir> | Diretório de saída | /tmp |
--send | Envia pro chat automaticamente | false |
--caption <text> | Caption ao enviar (com --send) | início do texto |
O comando retorna o path do áudio gerado + o comando pra enviar:
✓ Audio saved: /tmp/ravi-audio-1234567890.mp3
Send to chat: ravi media send "/tmp/ravi-audio-1234567890.mp3"
ravi audio generate "texto" — gera o MP3--send ou copie o comando ravi media send do output--lang pt pra melhor pronúnciaELEVENLABS_API_KEY no ~/.ravi/.envELEVENLABS_API_KEY — obrigatória, no ~/.ravi/.envELEVENLABS_VOICE_ID — voice padrão (opcional)npx claudepluginhub filipexyz/ravi --plugin ravi-systemGenerates realistic AI text-to-speech audio using Google Gemini TTS, ElevenLabs, and OpenAI TTS. Supports multi-speaker dialogues, podcasts, audiobooks, and voiceovers.
Generate audio content — text-to-speech, podcasts, voice cloning, sound effects, speech-to-speech, dubbing, and audio isolation. Currently powered by ElevenLabs. Works with both the Python SDK and the ElevenLabs CLI. Includes ready-to-run generator scripts that Claude writes to a temp file and executes directly. Triggers: audio, elevenlabs, text-to-speech, TTS, podcast, voice, voiceover, narration, voice clone, sound effects, dubbing, speech-to-speech, audio isolation.
Generates voiceover audio via ElevenLabs TTS API with direct curl calls, voice tuning, and sound effects. For narration, audio ducking, and multilingual production — not voice AI agents or transcription.