STT-tool
DavidArakelyan/STT-tool
Speech-to-Text service with multi-provider support (HiSpeech, Gemini, ElevenLabs) and Armenian language optimization
speech-to-textarmenian-languageapi-serviceaudio-processingspeaker-diarizationmachine-learningdockercelery
Summary
A robust Speech-to-Text (STT) service with multi-provider API integration (Google Gemini, ElevenLabs, Whisper, HiSpeech), featuring speaker diarization, smart audio chunking, and specialized optimizations for Armenian language transcription. It offers a full-stack solution with a REST API, modern web UI, and a Dockerized backend using PostgreSQL, Redis, MinIO, and Celery.