local-voiceLocal text-to-speech (TTS) and speech-to-text (STT) using FluidAudio on Apple Silicon. Sub-second voice synthesis and transcription running entirely on-device via the Apple Neural Engine. Use when setting up local voice capabilities, voice assistant integration, or replacing cloud TTS/STT services.
Install via ClawdBot CLI:
clawdbot install TrondW/local-voiceGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → http://127.0.0.1:18790/synthesizeCalls external URL not in known-safe list
http://www.apple.com/DTDs/PropertyList-1.0.dtdAI Analysis
The skill runs a local daemon on 127.0.0.1 and uses only local system resources (brew, launchctl) and a public Apple DTD. No data is sent to external servers, and all operations are consistent with the stated purpose of local TTS/STT.
Audited Apr 16, 2026 · audit v1.0
Generated Mar 20, 2026
Integrate the skill into a voice assistant application to enable offline, private voice interactions. This is ideal for smart home systems or personal assistant apps that require real-time, low-latency TTS and STT without cloud dependency.
Use the TTS feature to generate pronunciation examples and STT for speech practice in language learning apps. The low latency and multiple language support enhance interactive learning experiences on macOS devices.
Implement the skill in macOS applications to provide voice-based navigation and content reading for users with visual impairments. The local processing ensures data privacy and works offline in various settings.
Leverage the TTS with expressiveness controls to generate voiceovers for videos, podcasts, or audiobooks. The sub-second synthesis speeds up production workflows while maintaining high-quality, customizable audio output.
Integrate STT for transcribing patient consultations or medical notes in healthcare applications on Apple Silicon Macs. The local processing ensures compliance with data privacy regulations like HIPAA by avoiding cloud transmission.
Offer a basic version of the skill for free with limited voices or features, and charge for premium access to all 54 voices, advanced SSML tags, or priority support. This model targets developers and small businesses looking to integrate local voice capabilities.
Provide custom integration and support services for large organizations adopting the skill into their existing systems, such as call centers or internal tools. Revenue comes from consulting, customization, and ongoing maintenance contracts.
Partner with Apple or hardware vendors to pre-install the skill on macOS devices targeted at specific industries like education or healthcare. This creates a value-added offering that enhances device functionality and drives sales.
💬 Integration Tip
Ensure all dependencies like espeak-ng are installed and the binary is correctly placed with the framework to avoid runtime errors; test the API endpoints with sample scripts before full integration.
Scored Apr 19, 2026
Local speech-to-text with the Whisper CLI (no API key).
Transcribe audio files with speaker diarization (who speaks when). Supports 100+ languages, automatic language detection, and timestamps. Use for meetings, interviews, podcasts, or voice messages. Requires AssemblyAI API key.
Search and manage Spotify playlists, tracks, albums, artists, and playback state via the Spotify Web API. Use this skill when users want to search for music,...
使用 poocr 库识别发票并导出 Excel。当用户需要识别增值税发票、批量处理发票文件或提取发票信息到 Excel 时调用此技能。
Transcribe long audio files safely on 16GB RAM machines using auto-chunking with Whisper’s base model and seamless transcript merging.
Use when the user has audio or video and wants a timestamped transcript (SRT) in the source language. Routes by source language — Chinese defaults to Volcano...