/xtts-streaming-server

Primary LanguagePythonMozilla Public License 2.0MPL-2.0

XTTS streaming server

Running the TTS server

  1. Create a conda environment and activate it conda create -n tts python=3.11; conda activate tts
  2. Install requirements with pip install -r requirements.txt --use-deprecated=legacy-resolver
  3. Run the server
$ cd tts-server
$ uvicorn main:app --host 0.0.0.0 --port 8000
  1. Run the client
$ cd client
$ python tts.py --ref_file reference_audio_file_for_cloning.wav --text "text to dictate"

TODOs

  • add utterance timing detection to speech recognition server
  • modify speech synthesis server to support main async client
  • connect and test chat_completions endpoint with LMStudio API