Skip to Content
👋 欢迎来到 HowToUseOpenClaw 快速入门
技能目录语音与转录

语音与转录

本类别技能用于 语音与转录。使用 npx clawdhub@latest install <skill-slug> 安装任意技能。

技能列表

assemblyai-transcribe

描述: Transcribe audio/video with AssemblyAI (local upload.

安装:

npx clawdhub@latest install assemblyai-transcribe

audio-gen

描述: Generate audiobooks, podcasts, or educational audio content on demand.

安装:

npx clawdhub@latest install audio-gen

audio-reply

描述: Generate audio replies using TTS. Trigger with “read it to me [URL]” to fetch.

安装:

npx clawdhub@latest install audio-reply-skill

edge-tts

描述: 见 ClawdHub 页面

安装:

npx clawdhub@latest install edge-tts

gettr-transcribe-summarize

描述: Download audio from a GETTR post (via HTML og:video), transcribe it locally.

安装:

npx clawdhub@latest install gettr-transcribe-summarize

llmwhisperer

描述: Extract text and layout from images and PDFs using LLMWhisperer API.

安装:

npx clawdhub@latest install llmwhisperer

local-whisper

描述: Local speech-to-text using OpenAI Whisper. Runs fully offline after model download.

安装:

npx clawdhub@latest install local-whisper

mlx-whisper

描述: Local speech-to-text with MLX Whisper (Apple Silicon optimized, no API key).

安装:

npx clawdhub@latest install mlx-whisper

openai-whisper

描述: Local speech-to-text with the Whisper CLI (no API key).

安装:

npx clawdhub@latest install openai-whisper

openai-whisper-api

描述: Transcribe audio via OpenAI Audio Transcriptions API (Whisper).

安装:

npx clawdhub@latest install openai-whisper-api

parakeet-mlx

描述: Local speech-to-text with Parakeet MLX (ASR) for Apple Silicon (no API key).

安装:

npx clawdhub@latest install parakeet-mlx

parakeet-stt

描述: >-.

安装:

npx clawdhub@latest install parakeet-stt

pocket-transcripts

描述: Read transcripts and summaries from Pocket AI (heypocket.com) recording devices.

安装:

npx clawdhub@latest install heypocket-reader

pocket-tts

描述: pocket-tts

安装:

npx clawdhub@latest install pocket-tts

tts-whatsapp

描述: Send high-quality text-to-speech voice messages on WhatsApp in 40+ languages with automatic delivery.

安装:

npx clawdhub@latest install tts-whatsapp

video-subtitles

描述: Generate SRT subtitles from video/audio with translation support.

安装:

npx clawdhub@latest install video-subtitles

voice-transcribe

描述: Transcribe audio files using OpenAI’s gpt-4o-mini-transcribe model with vocabulary hints.

安装:

npx clawdhub@latest install voice-transcribe

elevenlabs-voices

描述: ElevenLabs voice synthesis: 18 personas, 32 languages, sound effects.

安装:

npx clawdhub@latest install elevenlabs-voices

elevenlabs-media

描述: ElevenLabs music generation and speech-to-text (Scribe v2).

安装:

npx clawdhub@latest install clawdbotborges

elevenlabs-agents

描述: Create and manage ElevenLabs conversational AI agents.

安装:

npx clawdhub@latest install elevenlabs-agents

tts

描述: Text-to-speech using Hume AI or OpenAI API.

安装:

npx clawdhub@latest install tts

相关资源

最后更新于: