Telegram Voice Bot

Telegram bot that transcribes voice messages using Whisper and replies in Chinese with Microsoft Edge text-to-speech.

This skill appears to do what it claims, but take these precautions before installing: (1) run it in an isolated environment (virtualenv/container) because Whisper will download model files and may use substantial disk/CPU; (2) ensure you supply only a Bot token created for this bot (keep it secret); (3) verify which Whisper package/version you want (SKILL.md says openai-whisper but requirements.txt lists 'whisper'); (4) understand that voice data is downloaded from Telegram and sent to edge-tts (third-party TTS service) for synthesis — if privacy is a concern, review edge-tts behavior and network endpoints; (5) review and pin dependency versions before production use and monitor network activity on first run.

Type: OpenClaw Skill Name: telegram-voice-bot Version: 2.0.0 The skill implements a Telegram bot for voice-to-text and text-to-voice processing using OpenAI Whisper and Microsoft Edge TTS. The code in `bot.py` is well-structured and strictly follows its stated purpose, handling Telegram API interactions and audio processing without any signs of data exfiltration, unauthorized network calls, or malicious execution. While `requirements.txt` specifies `whisper` instead of `openai-whisper` (which would cause a functional error during execution), this appears to be a common developer oversight rather than an intentional supply-chain attack.