aiola-lab/drax
Drax: Speech Recognition with Discrete Flow Matching
This project helps convert spoken words in audio recordings into written text. You provide an audio file in a specific language, and it outputs a precise transcript of what was said. This tool is for researchers, developers, or linguists who need to automatically process and analyze spoken language.
Use this if you need to accurately transcribe audio files into text for various applications.
Not ideal if you are looking for a plug-and-play application with a graphical user interface.
Stars
75
Forks
4
Language
Python
License
—
Category
Last pushed
Oct 15, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/aiola-lab/drax"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
index-tts/index-tts
An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System
stepfun-ai/Step-Audio-EditX
A powerful 3B-parameter, LLM-based Reinforcement Learning audio edit model excels at editing...
lucasnewman/f5-tts-mlx
Implementation of F5-TTS in MLX
unilight/seq2seq-vc
A sequence-to-sequence voice conversion toolkit.
FireRedTeam/FireRedTTS
An Open-Sourced LLM-empowered Foundation TTS System