local-voice-replyLocal OPUS/Ogg voice-reply pipeline for Feishu/Discord with structured voice customization. Default voice is Juno (`voice/juno_ref.wav`), with support for re...
Install via ClawdBot CLI:
clawdbot install tenured-master-chef-607/local-voice-replyGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
http://127.0.0.1:8000/docsAudited Apr 17, 2026 · audit v1.0
Generated Mar 20, 2026
Enables automated voice responses in customer service chatbots on Feishu or Discord, providing personalized audio replies using cloned agent voices for a more engaging support experience. Useful for handling common queries with low-latency, locally generated audio to reduce response times.
Allows educators to create custom voice narrations for online courses or tutorials on platforms like Discord, using registered voices to match different instructors or characters. Supports structured voice customization for multilingual or accent-specific educational materials.
Facilitates voice-based interactions in gaming communities on Discord, where bots can generate audio replies in custom voices for announcements, role-playing, or event notifications. Enhances immersion by allowing voice cloning of community figures or game characters.
Integrates with Feishu for internal team communications, enabling voice messages from AI assistants in cloned manager or team member voices for announcements, reminders, or training. Provides a personalized touch while maintaining data privacy through local processing.
Supports accessibility applications by converting text to speech in custom voices for Feishu or Discord, allowing users to register familiar voices for a more natural listening experience. Helps in making digital content more accessible with low-latency audio generation.
Offers a cloud-based service where users pay a monthly fee to access advanced voice customization features, such as unlimited voice registrations and premium voice models. Revenue is generated through tiered subscriptions based on usage limits and support levels.
Provides enterprise clients with licenses to integrate the skill into their existing Feishu or Discord workflows, including custom development, support, and training. Revenue comes from one-time setup fees and annual maintenance contracts tailored to business needs.
Offers a free basic version with limited voice options and usage, while charging for higher API call volumes, additional voice slots, and priority support. Revenue is generated from pay-as-you-go API credits and premium feature unlocks for power users.
💬 Integration Tip
Ensure ffmpeg is installed on PATH and Python dependencies are correctly set up; use the provided scripts for stable generation to avoid common path errors.
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...