tts / README.md
waxz
change MODELS env
2d85dce
metadata
title: Tts
emoji: 
colorFrom: blue
colorTo: gray
sdk: docker
pinned: false
short_description: openai api style tts engine

tts-proxy

A simple openai api style tts server based on supertonic.

install dependencies

curl -LsSf https://astral.sh/uv/install.sh | sh
uv venv -p 3.10
source .venv/bin/activate
uv pip install -r ./requirements.txt

run server

export API_KEY=yourapi
export MODELS='{"tts-1": "kokoro", "tts-2": "supertonic"}'
python app.py

run client

curl http://localhost:8000/v1/audio/speech   -H "Content-Type: application/json"  -H "Authorization: Bearer yourapi"  -d '{
    "model": "tts-1",
    "input": "Hello World! Come Here!",
    "voice": "F1",
    "format": "wav"
  }'   --output ./test.wav

curl http://localhost:8000/v1/audio/speech   -H "Content-Type: application/json"  -H "Authorization: Bearer yourapi"  -d '{
    "model": "tts-1",
    "input": "Hello World! Come Here!",
    "voice": "F1",
    "format": "mp3"
  }'   --output ./test.mp3