telegram-multilingual-voice-replySmart Telegram reply workflow for OpenClaw: if the user sends text, reply with text; if the user sends a voice note/audio, transcribe locally using the insta...
Install via ClawdBot CLI:
clawdbot install pengling9405/telegram-multilingual-voice-replyGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/Blaizzy/mlx-audio/blob/main/mlx_audio/stt/models/qwen3_asr/REAudited Apr 17, 2026 · audit v1.0
Generated Mar 21, 2026
Businesses use this skill to handle customer inquiries on Telegram, automatically replying with text or voice in the user's language. It reduces response time and supports multilingual customers without human intervention, ideal for e-commerce or service platforms.
Language learners interact via Telegram to practice speaking and listening. The skill transcribes their voice, provides feedback in the same language, and sends voice replies for pronunciation practice, enhancing engagement through conversational AI.
Individuals use this skill to manage tasks or get reminders via Telegram. They can send voice notes for hands-free input, receive voice and text replies for confirmation, and follow up in their preferred language, streamlining daily workflows.
Healthcare providers integrate this skill for initial patient consultations on Telegram. Patients describe symptoms via voice, get transcribed and analyzed, and receive voice and text replies in their language, improving accessibility in remote areas.
Entertainment platforms deploy this skill for interactive chatbots on Telegram. Users engage with voice or text, receive humorous or informative replies in the same language via voice notes, enhancing user experience in gaming or social apps.
Offer this skill as a cloud-based service with monthly or annual subscriptions. Businesses pay for usage tiers based on message volume or language support, generating recurring revenue while providing scalable AI-powered communication tools.
Provide a free basic version with limited languages or reply types. Monetize through premium upgrades like advanced language support, custom TTS voices, or higher accuracy ASR, attracting individual users and small businesses.
Sell enterprise licenses for large organizations needing custom integration, enhanced security, and dedicated support. Revenue comes from one-time fees or annual contracts, targeting industries like healthcare or finance with strict compliance needs.
💬 Integration Tip
Ensure the Python environment has mlx_audio installed and test audio format compatibility with Telegram's ogg/opus files to avoid transcription failures.
Scored Apr 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 text-to-speech via sherpa-onnx (offline, no cloud)
Start voice calls via the OpenClaw voice-call plugin.