ClawHub

Telegram Voice Bot

v2.0.0

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

⭐ 0· 204·0 current·0 all-time
by@polityang
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description match the code and SKILL.md: the bot polls Telegram, downloads voice files, runs Whisper locally to transcribe, and uses edge-tts to synthesize Chinese replies. Required resources (model downloads, network access to Telegram and TTS services) are appropriate for this purpose.
✓
Instruction Scope
SKILL.md and bot.py keep scope to Telegram voice handling: they require TELEGRAM_BOT_TOKEN and optionally VOICE_REPLY, instruct running bot.py, and do not read unrelated system files or attempt to exfiltrate arbitrary data to third-party endpoints beyond Telegram and the TTS service (accessed via edge-tts).
ℹ
Install Mechanism
This is instruction-only (no install spec). requirements.txt lists requests, whisper, and edge-tts; installing these will pull Python packages and Whisper will download (potentially large) model files at runtime. Note: SKILL.md mentions 'openai-whisper' while requirements.txt lists 'whisper' — verify the intended package name/version before install. No suspicious external download URLs or installers are present.
✓
Credentials
Only TELEGRAM_BOT_TOKEN (and optional VOICE_REPLY) are used. No unrelated credentials or config paths are requested. The token is necessary and sufficient for the bot to access the Telegram Bot API.
✓
Persistence & Privilege
Skill does not request permanent 'always' presence, does not modify other skills or system-wide settings, and does not persist credentials. Autonomous invocation is allowed by default (normal) but not escalated by the skill itself.
Assessment
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.

Like a lobster shell, security has layers — review code before you run it.

latestvk974ajg5rrm12ye3xb9cbrn9sx82t3s0

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments