← Back to Skills Marketplace
772
Downloads
0
Stars
3
Active Installs
1
Versions
Install in OpenClaw
/install telegram-voice
Description
Voice communication via Telegram. Automatically transcribes incoming voice messages using faster-whisper and replies with TTS voice. Use for all voice-relate...
Usage Guidance
This skill appears coherent for Telegram voice transcription and TTS replies. Before installing or enabling it: confirm you trust the faster-whisper package and are comfortable allowing a pip install (it will pull third-party code and download model weights which can be large); ensure your agent/platform already has Telegram credentials and a TTS tool configured (the skill expects those but does not manage them); consider running installations in a controlled environment if you want to limit supply-chain risk or disk/network usage.
Capability Analysis
Type: OpenClaw Skill
Name: telegram-voice
Version: 1.0.0
The skill bundle provides standard functionality for Telegram voice communication, utilizing the 'faster-whisper' library for transcription and a built-in TTS tool for replies. The instructions and code snippets in SKILL.md are consistent with the stated purpose and do not exhibit any signs of malicious intent, data exfiltration, or unauthorized execution.
Capability Assessment
Purpose & Capability
Name/description (Telegram voice transcription + TTS replies) matches the instructions: they show using faster-whisper to transcribe .ogg files and using an existing TTS/send tool to reply. The skill does not request unrelated credentials or tools.
Instruction Scope
SKILL.md stays on task: it shows a small faster-whisper snippet for transcribing a local file path and JSON actions for sending TTS replies to the Telegram channel. It does not instruct reading arbitrary files, other env vars, or exfiltrating data to unexpected endpoints.
Install Mechanism
There is no install spec, but SKILL.md advises installing faster-whisper via pip. Pip installs and model downloads are normal for this purpose but involve executing third-party code and downloading model weights from upstream—this is a legitimate functional requirement but carries the usual supply-chain and resource risks (bandwidth, disk).
Credentials
The skill declares no required env vars or credentials. It implicitly relies on the agent/platform having Telegram and TTS capability already configured; it does not ask for unrelated secrets or broad access.
Persistence & Privilege
always is false and the skill does not request persistent or system-wide privileges. It does not ask to modify other skills or agent configs.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install telegram-voice - After installation, invoke the skill by name or use
/telegram-voice - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of Telegram voice communication skill.
- Automatically transcribes incoming Telegram voice messages (.ogg) using faster-whisper.
- Replies to users with synthesized voice messages using TTS.
- Supports auto-detection or specification of input language.
- Designed for all voice-related interactions on Telegram.
Metadata
Frequently Asked Questions
What is Voice?
Voice communication via Telegram. Automatically transcribes incoming voice messages using faster-whisper and replies with TTS voice. Use for all voice-relate... It is an AI Agent Skill for Claude Code / OpenClaw, with 772 downloads so far.
How do I install Voice?
Run "/install telegram-voice" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Voice free?
Yes, Voice is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Voice support?
Voice is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Voice?
It is built and maintained by Polityang (@polityang); the current version is v1.0.0.
More Skills