Indri

Multimodal audio LMs for TTS, ASR, and voice cloning

Running locally

Prerequisites

• Python 3.10+
• CUDA 12.1+

Install dependencies:

pip install -r requirements.txt

Install ffmpeg:

For linux:

sudo apt update -y
sudo apt upgrade -y
sudo apt install ffmpeg -y

Running the service

python -m inference --model_path 11mlabs/indri-0.1-124m-tts --device cuda:0 --port 8000

Defaults:

• device: cuda:0
• port: 8000

Choices:

• model_path: HuggingFace collection

Redirect to http://localhost:8000/docs to see the API documentation and test the service.