claw-voice-localConvert text to offline Telegram voice messages using piper TTS. Use when the agent should speak a response, send audio, or deliver voice notes via Telegram...
Install via ClawdBot CLI:
clawdbot install photon78/claw-voice-localGrade 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/rhasspy/piperUses known external API (expected, informational)
api.telegram.orgAudited Apr 24, 2026 · audit v1.0
Generated Oct 2, 2026
A Raspberry Pi running OpenClaw controls smart home devices and sends spoken confirmations via Telegram when sensors trigger or routines complete. Users receive offline voice notes like 'Garage door closed' or 'Motion detected in backyard' without cloud dependency. Ideal for privacy-conscious homes protecting sensitive routines from third-party servers.
Agents deployed in areas with poor connectivity send voice updates through Telegram when workers cannot read text on mobile screens. The offline piper TTS generates clear audio summaries of task status, safety alerts, or route changes. This keeps field crews informed through audio even when internet access is intermittent.
An AI agent monitors emails, calendars, and system events, then converts important notifications into Telegram voice messages using local TTS. Visually impaired users receive natural-sounding audio alerts on their phones without needing screen readers or cloud services. This improves independence for daily task management.
Community mesh networks or remote research stations use the skill to broadcast voice announcements via Telegram bots during emergencies or scheduled briefings. The offline TTS ensures alerts like weather warnings or evacuation notices are delivered as audio even when internet infrastructure fails. This supports resilience in isolated or disaster-prone areas.
Tutors or automated study agents generate spoken summaries of lessons or quiz feedback as Telegram voice messages. Students on low-bandwidth connections can listen to audio notes instead of downloading large files. The offline nature also supports schools with restricted internet access or data caps.
Offer a monthly subscription for a home or small-business AI assistant that uses local TTS for voice notifications via Telegram. Customers value that no text or audio leaves their premises, unlike cloud-based voice assistants. The subscription includes setup, updates, and premium voice models.
Sell a Raspberry Pi-based hardware kit preconfigured with the skill, piper, and a Telegram bot for plug-and-play voice messaging. Target makers, hobbyists, and small businesses needing offline automation. Revenue comes from hardware sales plus optional support plans.
License the skill to enterprises requiring air-gapped or offline voice alerting for internal systems like factories, hospitals, or remote sites. Provide integration services, custom voice models, and priority support. Pricing based on number of agents or nodes.
💬 Integration Tip
Ensure piper binary and a compatible .onnx voice model are installed on the host system, and set TELEGRAM_BOT_TOKEN with restricted permissions (chmod 600) in ~/.openclaw/.env. For ARM64 devices like Raspberry Pi, verify the piper release matches the architecture to avoid runtime errors.
Scored Oct 2, 2026
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.
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。
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...
Create, manage, and deploy ElevenLabs conversational AI agents. Use when the user wants to work with voice agents, list their agents, create new ones, or manage agent configurations.
Voice note transcription and archival for OpenClaw agents. Powered by Deepgram Nova-3. Transcribes audio messages, saves both audio files and text transcript...
Text-to-Speech (TTS) and Speech-to-Text (ASR) using coze-coding-dev-sdk. Returns results directly to stdout.