Home/Developer Tools/voicy

voicy

backmeupplz/voicy

@voicybot Telegram bot main repository

GitHub Website

GraphCanon updated 3w · GitHub synced 3w

905 stars164 forksLast push 3w JavaScript MIT

Decision brief

Voicy is an open-source speech-to-text Telegram bot, available under MIT license and requiring MongoDB and FFmpeg for setup.

Good fit when

You need to integrate speech-to-text capabilities into a Telegram bot using JavaScript.
Your project relies on local setups where full control over database (MongoDB) and transcription (FFmpeg) services is necessary.

Avoid when

If your project doesn't require or support running MongoDB locally for storing voice messages and their text transcriptions.
When you prefer cloud-based solutions for speech-to-text functionality without the need to manage FFmpeg for local processing tasks.

Observed Jul 16, 2026 · Source: enrich:decision_facts

voicy alternatives Trust report

Verify the decision

Maintenance and security

Full trust report

Maintenance: Very active (2d since push); As of 3w
Provenance: Not a fork · Personal account; As of 3w
Security (OSV): No lockfile; As of 1mo

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

npm install voicy

npm

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

OpenVoice

Instant voice cloning using an audio foundation model

37k★

vosk-api

Offline speech recognition API

15k★

voice-pro

Gradio WebUI for TTS and voice cloning with audio processing capabilities

11k★

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

A JavaScript-based Telegram bot focusing on speech-to-text functionality, requiring MongoDB and FFmpeg for local setup.

Capability facts

MCP server: No MCP server detected
Source: repo_scan · Jul 31, 2026
Languages: javascript, typescript
Source: github.language+package.json · Jul 31, 2026

README

Installation and local launch

Clone this repo: git clone https://github.com/backmeupplz/voicy
Launch a mongo database locally
Create .env file with the environment variables listed below
Install ffmpeg on machines that run local transcription workers
Run yarn in the root folder
Run yarn start

License

MIT — use for any purpose. Would be great if you could leave a note about the original developers. Thanks!

For agents

This page has a .md twin and JSON over the API.

/tools/backmeupplz-voicy.md GET /api/graphcanon/tools/backmeupplz-voicy GET /api/graphcanon/graph?tool=backmeupplz-voicy