Skip to content
/ plato-dev Public

Performant & scalable speech-to-text and text-to-speech layers for voice conversations with LLM agents.

License

Notifications You must be signed in to change notification settings

tkhv/plato-dev

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

plato-dev

Performant & scalable speech-to-text and text-to-speech layers for any voice-conversational LLMs.

To run the WhisperLiveServer, cd into WhisperLiveServer and run:

GPU

docker build -f Dockerfile.gpu -t whisperlive-gpu .
docker run -it --gpus all -p 9090:9090 --rm whisperlive-gpu

TensorRT

docker build -f Dockerfile.tensorrt -t whisperlive-tensorrt .
docker run -it --gpus all -p 9090:9090 --rm whisperlive-tensorrt

CPU

docker build -f Dockerfile.cpu -t whisperlive-cpu .
docker run -it -p 9090:9090 --rm whisperlive-cpu

To run an example app that uses the WhisperLiveServer to transcribe, cd into app and run app.py.

/tools/ contains Go scripts that can be used to record and re-play a Twilio call's websocket stream.

About

Performant & scalable speech-to-text and text-to-speech layers for voice conversations with LLM agents.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published