her-voiceGive your agent a voice. Use when the user wants the agent to speak, read aloud, or have voice responses.
Install via ClawdBot CLI:
clawdbot install matusvojtek/her-voiceGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
rm -rf ~Calls external URL not in known-safe list
https://brew.shAudited Apr 17, 2026 · audit v1.0
Generated Mar 21, 2026
Integrate Her Voice into customer service chatbots to provide audio responses for visually impaired users, enhancing accessibility. The on-the-fly streaming ensures low latency, making interactions feel natural and responsive, while the local TTS eliminates API costs.
Use Her Voice in language learning apps to read aloud text and provide pronunciation feedback, leveraging its configurable voice and speed settings. The daemon mode reduces latency for repeated exercises, and the visualizer on macOS can engage learners with real-time audio visualization.
Deploy Her Voice in personal assistant agents to read emails, reminders, or news articles aloud, using the persist mode as a standalone voice station. The notification sound gives immediate feedback, and the ability to save audio files allows for offline playback of important information.
Utilize Her Voice for generating voiceovers in content creation tools, such as podcast editing or video narration, by saving audio to WAV files. The Kokoro TTS model offers expressive voices, and the configurable settings allow fine-tuning for different content styles without external API dependencies.
Implement Her Voice in healthcare applications to read medical instructions or appointment reminders to patients, improving comprehension and adherence. The local processing ensures data privacy, and the setup wizard simplifies deployment across different platforms, including Apple Silicon for optimized performance.
Offer Her Voice as a free, open-source skill with premium features like advanced voice customization or cloud sync for configurations. Revenue can come from subscriptions for enterprise support, additional voice packs, or priority updates, leveraging the no-API-key appeal to attract users.
License Her Voice to businesses for integration into their proprietary software, such as call centers or educational platforms. Charge based on usage tiers or per-seat licenses, with revenue generated from ongoing support contracts and customization services for specific industry needs.
Partner with hardware manufacturers to bundle Her Voice with smart speakers, tablets, or kiosks, providing a local TTS solution that reduces cloud dependency. Revenue can come from upfront licensing fees per device sold or royalties based on sales volume, targeting markets where low latency and privacy are critical.
💬 Integration Tip
Ensure espeak-ng is installed and test the daemon for performance gains in high-frequency use cases, while providing text alternatives for accessibility compliance.
Scored Jun 19, 2026
Local speech-to-text with the Whisper CLI (no API key).
ElevenLabs text-to-speech with mac-style say UX.
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
Text-to-speech conversion using node-edge-tts npm package for generating audio from text. Supports multiple voices, languages, speed adjustment, pitch control, and subtitle generation. Use when: (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, driving, cooking). (3) User wants a specific voice, speed, pitch, or format for TTS output.
Local speech-to-text using OpenAI Whisper. Runs fully offline after model download. High quality transcription with multiple model sizes.
Text-to-speech via OpenAI Audio Speech API.