🎧 X2AGI Speech Kit for AI agents, humans, and robots

Feature	Emoji	Spec
Languages	🇷🇺 🇺🇸	Russian, English
Formats	🎵📺	.wav .flac .ogg .mp3 .mp4 and more
Duration	🕰️⚡️	Up to 10 hours long
Speakers	💯🗣️	Unlimited diarisation (hundreds of speakers)
Interfaces	🔌🏃	gRPC, REST, n8n, MCP
Quality	✨🎯	Punctuation, capitalisation, AI post-processing, no hallucination

Services available on x2agi.com via API

1. Audio Language Detection Service (lang-detect.x2agi.com). Documentation

2. Speech Recognition (ASR) and Diarization Service (stt-async.x2agi.com). Documentation

3. ASR Post-Processing Service: correction/punctuation/capitalization (postprocess-asr.x2agi.ru). Documentation

Installation

1. To use GRPC, install grpcio-tools

   pip install grpcio-tools

Visit our web-site.

To get an API key, please, use our Telegram-bot.