linto-ai/linto-stt

An automatic speech recognition API

57
/ 100
Established

Supports multiple interchangeable STT engines (NeMo, Whisper, Kaldi, Kyutai) deployed across three operational modes—HTTP for batch file processing, WebSocket for real-time streaming, and Celery task queues for async microservices architectures. Built with pluggable engine architecture and optional post-processing via recasepunc models for punctuation/capitalization on untrained outputs. Containerized with single Dockerfile parametrization and GPU acceleration support for compute-intensive backends.

No Package No Dependents
Maintenance 13 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

81

Forks

21

Language

Python

License

AGPL-3.0

Last pushed

Mar 13, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/linto-ai/linto-stt"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.