Voice input/output for Claude Desktop — real-time speech-to-text via faster-whisper with biquad noise filtering and rule-based emotion detection, paired wi…
Voice input/output for Claude Desktop — real-time speech-to-text via faster-whisper with biquad noise filtering and rule-based emotion detection, paired with text-to-speech via edge-tts. Runs as a local HTTP server on localhost:5123 and exposes MCP tools for Claude Desktop integration. Requires external configuration file voice.config.toml which can be set via VOICE_CONFIG_PATH environment variable.
This page belongs to the OpenClaw Skills learning hub with install guides, category navigation, and practical links.