{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_939caz2xp5rv","handle":"whisper-telegram-mcp","url":"https://wellknown.network/agents/whisper-telegram-mcp","links":{"self":"https://wellknown.network/agents/whisper-telegram-mcp/record.json","html":"https://wellknown.network/agents/whisper-telegram-mcp","markdown":"https://wellknown.network/agents/whisper-telegram-mcp/record.md","api":"https://wellknown.network/api/v1/agents/whisper-telegram-mcp","status":"https://wellknown.network/api/v1/agents/whisper-telegram-mcp/status","claim":"https://wellknown.network/agents/whisper-telegram-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/whisper-telegram-mcp/claim.json","badge":"https://wellknown.network/agents/whisper-telegram-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/whisper-telegram-mcp/history","tools":"https://wellknown.network/api/v1/agents/whisper-telegram-mcp/tools"},"ard":{"identifier":"urn:air::server:whisper-telegram-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"whisper-telegram-mcp","summary":"MCP server for transcribing Telegram voice messages using Whisper, with Kokoro/OpenAI TTS voice replies","description":"# whisper-telegram-mcp\n\n> Transcribe and speak — two-way voice for Claude via Telegram\n\n[![CI](https://github.com/abid-mahdi/whisper-telegram-mcp/actions/workflows/ci.yml/badge.svg)](https://github.com/abid-mahdi/whisper-telegram-mcp/actions)\n[![Python](https://img.shields.io/badge/python-3.10%2B-blue)](https://www.python.org/)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)\n[![MCP](https://img.shields.io/badge/MCP-compatible-brightgreen)](https://modelcontextprotocol.io)\n[![Ko-fi](https://img.shields.io/badge/Buy%20me%20a%20coffee-Ko--fi-FF5E5B?logo=ko-fi)](https://ko-fi.com/abidmahdi)\n\n<!-- TODO: Add demo.gif here showing voice in → transcription → voice reply -->\n\nAn [MCP](https://modelcontextprotocol.io) server that gives Claude two-way voice capabilities via Telegram: transcribe incoming voice messages with Whisper, and reply with synthesized speech. Works with Claude Desktop, Claude Code, and any MCP-compatible client.\n\n## What It Does\n\n- **Transcribe local audio files** -- OGG, WAV, MP3, FLAC, and more\n- **Transcribe Telegram voice messages** -- pass a `file_id`, get text back\n- **Speak text as voice notes** -- synthesise speech and send back as OGG (plays as a voice note in Telegram)\n- **Two transcription backends** -- local [faster-whisper](https://github.com/SYSTRAN/faster-whisper) (free, private) or OpenAI Whisper API (cloud)\n- **Auto mode** -- tries local first, falls back to OpenAI if it fails\n- **Language detection** -- automatic or specify an ISO-639-1 code\n- **Word-level timestamps** -- optional fine-grained timing\n\n## Prerequisites\n\n| Feature | Requirement |\n|---------|-------------|\n| Transcription (local) | None — faster-whisper bundled via `[local]` extras |\n| Transcription (cloud) | `OPENAI_API_KEY` env var |\n| Voice replies — Kokoro (best quality) | **Docker** — run `docker run -p 8880:8880 ghcr.io/remsky/kokoro-fastapi-cpu:latest` |\n| Voice replies — OpenAI TTS (fallback) | `OPENAI_API_KEY` env var |\n| Voice re…","publisher":null,"homepage":"https://github.com/abid-mahdi/whisper-telegram-mcp","repository":"https://github.com/abid-mahdi/whisper-telegram-mcp/releases","version":"0.1.0","license":"MIT","protocols":["mcp"],"tags":["claude","kokoro","mcp","speech-to-text","telegram","transcription","tts","voice","whisper"],"pricing":null,"endpoints":[{"url":"pypi:whisper-telegram-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"media.speech-recognition","name":"Speech Recognition","confidence":1,"provenance":"declared"},{"slug":"communication.sms-voice","name":"SMS & Voice","confidence":1,"provenance":"declared"},{"slug":"media.speech-synthesis","name":"Speech Synthesis","confidence":1,"provenance":"declared"},{"slug":"productivity.tasks","name":"Tasks & To-do","confidence":0.745,"provenance":"derived"}],"categories":["communication","media","productivity"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"whisper-telegram-mcp","registry":"pypi","observedAt":"2026-10-22T23:26:43.362Z","publishedAt":"2026-03-30T19:07:57.593761Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"whisper-telegram-mcp","url":"https://pypi.org/project/whisper-telegram-mcp/","firstSeenAt":"2026-09-10T15:24:41.520Z","fetchedAt":"2026-10-22T23:25:46.064Z","normalizedAt":"2026-10-22T23:25:46.064Z"}]},"firstSeenAt":"2026-09-10T15:24:41.520Z","updatedAt":"2026-10-22T23:26:43.362Z"}