Installation

Docker Compose (Recommended)

Note

I'm using newer Docker Compsose features. If you are using an older version of Docker Compose, you may need need to update.

Download the necessary Docker Compose files

CUDACUDA (with CDI feature enabled)CPU

curl --silent --remote-name https://raw.githubusercontent.com/speaches-ai/speaches/master/compose.yaml
curl --silent --remote-name https://raw.githubusercontent.com/speaches-ai/speaches/master/compose.cuda.yaml
export COMPOSE_FILE=compose.cuda.yaml

curl --silent --remote-name https://raw.githubusercontent.com/speaches-ai/speaches/master/compose.yaml
curl --silent --remote-name https://raw.githubusercontent.com/speaches-ai/speaches/master/compose.cuda.yaml
curl --silent --remote-name https://raw.githubusercontent.com/speaches-ai/speaches/master/compose.cuda-cdi.yaml
export COMPOSE_FILE=compose.cuda-cdi.yaml

curl --silent --remote-name https://raw.githubusercontent.com/speaches-ai/speaches/master/compose.yaml
curl --silent --remote-name https://raw.githubusercontent.com/speaches-ai/speaches/master/compose.cpu.yaml
export COMPOSE_FILE=compose.cpu.yaml

Start the service

docker compose up --detach

Build from source

# NOTE: you need to install and enable [buildx](https://github.com/docker/buildx) for multi-platform builds

# Build image with CUDA support
docker compose --file compose.cuda.yaml build

# Build image without CUDA support
docker compose --file compose.cpu.yaml build

Docker

CUDACUDA (with CDI feature enabled)CPU

docker run \
  --rm \
  --detach \
  --publish 8000:8000 \
  --name speaches \
  --volume hf-hub-cache:/home/ubuntu/.cache/huggingface/hub \
  --gpus=all \
  ghcr.io/speaches-ai/speaches:latest-cuda

docker run \
  --rm \
  --detach \
  --publish 8000:8000 \
  --name speaches \
  --volume hf-hub-cache:/home/ubuntu/.cache/huggingface/hub \
  --device=nvidia.com/gpu=all \
  ghcr.io/speaches-ai/speaches:latest-cuda

docker run \
  --rm \
  --detach \
  --publish 8000:8000 \
  --name speaches \
  --volume hf-hub-cache:/home/ubuntu/.cache/huggingface/hub \
  ghcr.io/speaches-ai/speaches:latest-cpu

Build from source

docker build --tag speaches .

# NOTE: you need to install and enable [buildx](https://github.com/docker/buildx) for multi-platform builds
# Build image for both amd64 and arm64
docker buildx build --tag speaches --platform linux/amd64,linux/arm64 .

# Build image without CUDA support
docker build --tag speaches --build-arg BASE_IMAGE=ubuntu:24.04 .

Python (requires Python 3.12+ and uv package manager)

git clone https://github.com/speaches-ai/speaches.git
cd speaches
uv venv
source .venv/bin/activate
uv sync --all-extras
uvicorn --factory --host 0.0.0.0 speaches.main:create_app