voice-chat-bridge双向语音对话系统 - 语音识别转文字 + Edge TTS语音合成 + Cloudflare Tunnel公网访问
Install via ClawdBot CLI:
clawdbot install patrickgeek/voice-chat-bridgeGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/sveinbjornt/hear/releases/download/0.7/hear-0.7.zipAudited Apr 17, 2026 · audit v1.0
Generated Mar 22, 2026
Enables voice-based interaction for elderly individuals who may struggle with typing or reading small text. The bidirectional voice chat allows natural conversation, making technology more accessible and reducing digital barriers.
Provides real-time voice feedback for language learners to practice speaking and listening skills. The system can transcribe user speech for accuracy checks and generate native-like responses to improve fluency.
Integrates with platforms like Telegram or webhooks to offer voice-based customer support. Automates responses to common queries, reducing human workload while maintaining a personal touch through voice interactions.
Facilitates hands-free computing by converting text outputs to speech and accepting voice inputs. The local mode ensures privacy and low latency, enhancing independence in daily digital tasks.
Embedds into smart home systems or IoT devices to enable voice commands and responses. Uses the web interface or local playback for seamless control without relying on external cloud services.
Offers a free tier with basic voice features for personal use, while charging for advanced integrations, higher usage limits, and premium support. Targets developers building voice-enabled applications.
Licenses the skill package to companies for internal use, such as customer service bots or training tools. Includes customization, on-premise deployment options, and dedicated maintenance.
Provides cloud-based APIs for speech-to-text and text-to-speech functionalities, leveraging the skill's integration capabilities. Monetizes through pay-per-use or tiered pricing based on request volume.
💬 Integration Tip
Start with the local mode for quick testing, then scale to web or public access based on user feedback and deployment needs.
Scored Jun 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...