telegram-voice-to-voice-macosTelegram voice-to-voice for macOS Apple Silicon: transcribe inbound .ogg voice notes with yap (Speech.framework) and reply with Telegram voice notes via say+ffmpeg. Not compatible with Linux/Windows.
Install via ClawdBot CLI:
clawdbot install Fiberian1981/telegram-voice-to-voice-macosGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/finnvoor/yapAudited Apr 17, 2026 · audit v1.0
Generated Mar 21, 2026
This skill enables macOS Apple Silicon users to interact with Telegram via voice notes, transcribing incoming voice messages and replying with synthesized voice responses. It's ideal for hands-free communication, such as when driving or multitasking, by leveraging native macOS speech tools for accurate transcription and text-to-speech.
Designed for individuals with visual impairments, this skill converts Telegram voice notes to text for easy reading and replies with audio responses. It enhances accessibility by allowing users to engage in voice-based conversations without relying on screen readers, using macOS's Speech.framework for reliable transcription.
Language learners can use this skill to practice speaking and listening in Telegram chats. It transcribes voice notes in different languages (configurable via YAP_LOCALE) and replies with synthesized voice, helping users improve pronunciation and comprehension through immersive, real-time voice exchanges on macOS.
Small businesses can deploy this skill to handle customer inquiries on Telegram via voice notes, automatically transcribing requests and providing voice responses. It streamlines support by reducing typing effort, with persistent user preferences for voice or text replies, suitable for macOS-based support teams.
Content creators and podcasters can use this skill to transcribe voice notes from Telegram interviews or ideas and generate voice replies for editing or feedback. It integrates with ffmpeg for audio processing, enabling quick conversion of text to high-quality OGG files for production workflows on macOS.
Offer a free basic version with limited transcription accuracy and voice options, then charge a monthly subscription for advanced features like custom voices, higher accuracy locales, and priority support. Revenue comes from subscriptions targeting power users and businesses on macOS.
Sell the skill as a standalone software package with a one-time license fee, including lifetime updates and support. This model appeals to individual macOS users seeking a reliable, offline-capable voice-to-voice tool without ongoing costs, generating revenue from direct sales.
Provide enterprise licenses for businesses to integrate the skill into their Telegram-based workflows, such as customer support or internal communication. Revenue is generated through annual contracts that include customization, bulk user management, and dedicated technical support for macOS environments.
💬 Integration Tip
Ensure all required binaries (yap, ffmpeg, say, defaults) are installed and in PATH, and set up persistent state files in the workspace for user preferences to avoid runtime errors.
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.