Back: Catalog

WhisperLive

This project is an application that converts speech sounds into text in real time using the OpenAI Whisper model. Supports working with microphone input or pre-recorded audio files. On the server side, it offers three different infrastructure options: faster_whisper, tensort, and openvino.

WH

WhisperLive

New80

collabora · Voice & Text-to-Speech

STARS4.3K
FORKS609
COMMITS0
CONTRIBUTORS0
VERSIONv0.10.0
UPDATEDyesterday
PythonSpeech-to-TextWhisperReal-TimeMIT

Common commercial products in this category: ElevenLabs, Amazon Polly, Google Cloud Text-to-Speech

What can it do?
  • You can convert conversations from microphones or audio files to text in real time.
  • At word level, you can use advanced features such as time stamps, speaker distinction, and special vocabulary.
  • You can run servers by opting for faster_whisper, tensort, or openvino infrastructures.
User reviews
  • • NeutralGitHub Issue

    Simple Client Recording Attempt

    “I start up the server via $ `python ./run_server.py` ``` (whisper_live) whisperlive git:(main)✗ 🚀 python ./run_server.py Downloading: " to /Users/justinwinter/.cache/torch/hub/master.zip 2023-08-21 12:14:34.119619 [W:onnxruntime:, graph.cc:3543…”

  • • NeutralGitHub Issue

    Windows support?

    “Hi, I would like to know if Windows will be supported, I tried with the actual files but I am not able to make it work… Any hint on how to make it work would be welcome.”

GitHub

My note

Alternative pages

ElevenLabs alternativesAmazon Polly alternativesGoogle Cloud Text-to-Speech alternatives

More in: Voice & Text-to-Speech