telegram-voice

Transcribe Telegram audio messages with Whisper and reply via local TTS.

1|Updated Mar 24, 2026
One-click install
npx skills add https://github.com/rovanni/IalClaw --skill telegram-voice
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: telegram-voice
Source: https://github.com/rovanni/IalClaw/tree/main/skills/internal/telegram-voice
Command: npx skills add https://github.com/rovanni/IalClaw --skill telegram-voice

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Handle Telegram voice messages locally by transcribing incoming audio with Whisper and replying with natural-sounding voice using a local TTS engine, enabling private and instant audio interactions.

Core Features & Use Cases

  • Incoming Audio Processing (STT): Transcribe Telegram voice messages (.ogg) to text using Whisper.
  • Outgoing Audio Generation (TTS): Convert text responses into Telegram-compatible voice messages (.ogg) via local neural TTS.
  • Context Management: Select the most recent audio when multiple files are attached and seamlessly integrate with the conversation flow.
  • Privacy-first Processing: All transcription and synthesis occur on-device or within trusted infrastructure without exposing data externally.

Quick Start

Send a Telegram audio message to trigger transcription and a voice reply generated from the text.

Frequently Asked Questions about telegram-voice

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I transcribe Telegram voice messages locally without sending data to the cloud?

Transcribe Telegram voice messages locally by processing incoming .ogg audio files with Whisper for STT. This ensures private voice transcription without exposing your audio data to external APIs or cloud services.

Can I reply to Telegram chats with generated voice messages using local TTS?

Reply to Telegram chats with generated voice messages by converting text responses into Telegram-compatible .ogg files using local neural TTS. The synthesized audio is formatted specifically for Telegram voice message delivery.

Does Whisper support processing multiple audio files attached in one Telegram message?

Whisper processing supports multiple audio files by applying context-aware file selection to identify and transcribe the most recent audio attachment. This ensures the correct voice message is processed during multi-file Telegram scenarios.

What is the best way to handle private Telegram audio interactions end to end?

Handle private Telegram audio interactions by using Whisper for on-device speech-to-text and thorial-tts for text-to-speech. This privacy-first approach keeps both transcription and synthesis within trusted infrastructure without external data exposure.

Do I need an internet connection to convert Telegram audio cues into spoken responses?

You do not need an external internet connection to convert Telegram audio cues into spoken responses. On-device STT via Whisper and local TTS handle the processing, ensuring real-time voice feedback without external network dependencies.

Why use local STT and TTS for Telegram voice messages instead of cloud APIs?

Use local STT and TTS for Telegram voice messages instead of cloud APIs to maintain strict data privacy. Local processing via Whisper and neural TTS prevents external data exposure while providing instant, real-time audio interaction feedback.