Skills, plugins and agents for Audio &amp; voice

1. Download the runtime for your OS (extracts into `$OPENCLAW_STATE_DIR/tools/sherpa-onnx-tts/runtime`, default `~/.openclaw/tools/sherpa-onnx-tts/runtime`)

OpenAI transcriptions API

Transcribe audio through `/v1/audio/transcriptions`. Set `OPENAI_BASE_URL` for an OpenAI-compatible proxy or local gateway.

Whisper (CLI)

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Text to speech (ElevenLabs TTS)

Use `sag` for ElevenLabs TTS with local playback.

songsee

Generate spectrograms + feature panels from audio.

Albums de musique

★102.4k

Full-lifecycle AI music album production : concept, lyric drafting, track sequencing, and export. Useful for indie album experiments and brand soundtr

nexu-io

Audio lecture on Venice

★102.4k

Text-to-speech models, voices, formats, and streaming via Venice.ai. Useful for narration, voiceover, and conversational agent voices.

nexu-io

Musique de venise

★102.4k

Music generation queueing, retrieval, and completion endpoints via Venice.ai. Suited for jingles, background loops, and prototype scoring.

nexu-io

Click anywhere on MuseScore

★54.9k

Command-line interface for music notation: transposition, export to PDF/audio/MIDI, part extraction, and management of instruments

HKUDS

Click anywhere in Audacity

★54.9k

Command-line interface for Audacity - A stateful command-line interface for audio editing, following the same patterns as the GIMP and Ble...

HKUDS

Azure ai transcription py

SDK Azure AI Transcription for Python. Use it for real-time and batch speech-to-text transcription, with timestamping and diarization.

Azure ai voicelive ts

SDK Azure AI Voice Live for JavaScript/TypeScript. Build real-time voice AI applications using bidirectional WebSocket communication

Azure for Voicelive Java

SDK Azure AI VoiceLive for Java. Real-time, two-way voice conversations with AI assistants via WebSocket.

Azure voice live .net

SDK Azure AI Voice Live for .NET. Build real-time voice AI applications using bidirectional WebSocket communication.

Azure, I'm going live on py.

Build real-time voice AI applications using bidirectional WebSocket communication.

Transcripteur audio

Turn your audio recordings into professional-quality Markdown documentation with smart summaries, thanks to the integration of a

Audio transcription (ElevenLabs Scribe)

★1.3k

Transcribe audio or video files using the ElevenLabs Speech-to-Text API (Scribe v2). Accepts a file path and optional parameters, reads the API key from the project's .env file, and returns a formatte

qdhenry

Openai Whisper

★325

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

Video Subtitles

★17

Generate SRT subtitles from video/audio with translation support. Transcribes Hebrew (ivrit.ai) and English (whisper), translates between languages, burns subtitles into video. Use for creating captions, transcripts, or

Local Whisper

★12

Local speech-to-text using OpenAI Whisper. Runs fully offline after model download. High quality transcription with multiple model sizes.

Songsee

★10

Generate spectrograms and feature-panel visualizations from audio with the songsee CLI.

Voice Wake Say

★5

Speak responses aloud on macOS using the built-in `say` command when user input indicates Voice Wake/voice recognition (for example, messages starting with "User talked via voice recognition on <device>").