├── .github
└── workflows
│ └── docker-build-push.yml
├── .gitignore
├── Dockerfile
├── LICENSE
├── README.md
├── config.py
├── dia
├── __init__.py
├── audio.py
├── config.py
├── layers.py
├── model.py
└── state.py
├── docker-compose.yml
├── documentation.md
├── download_model.py
├── engine.py
├── env.example.txt
├── models.py
├── reference_audio
├── Gianna.txt
├── Gianna.wav
├── Oliver_Luna.txt
├── Oliver_Luna.wav
├── Robert.txt
└── Robert.wav
├── requirements.txt
├── server.py
├── static
├── screenshot-d.png
└── screenshot-l.png
├── ui
├── index.html
├── presets.yaml
└── script.js
├── utils.py
└── voices
├── Abigail.txt
├── Abigail.wav
├── Abigail_Taylor.txt
├── Abigail_Taylor.wav
├── Adrian.txt
├── Adrian.wav
├── Adrian_Jade.txt
├── Adrian_Jade.wav
├── Alexander.txt
├── Alexander.wav
├── Alexander_Emily.txt
├── Alexander_Emily.wav
├── Alice.txt
├── Alice.wav
├── Austin.txt
├── Austin.wav
├── Austin_Jeremiah.txt
├── Austin_Jeremiah.wav
├── Axel.txt
├── Axel.wav
├── Axel_Miles.txt
├── Axel_Miles.wav
├── Connor.txt
├── Connor.wav
├── Connor_Ryan.txt
├── Connor_Ryan.wav
├── Cora.txt
├── Cora.wav
├── Cora_Gianna.txt
├── Cora_Gianna.wav
├── Elena.txt
├── Elena.wav
├── Elena_Emily.txt
├── Elena_Emily.wav
├── Eli.txt
├── Eli.wav
├── Emily.txt
├── Emily.wav
├── Everett.txt
├── Everett.wav
├── Everett_Jordan.txt
├── Everett_Jordan.wav
├── Gabriel.txt
├── Gabriel.wav
├── Gabriel_Ian.txt
├── Gabriel_Ian.wav
├── Gianna.txt
├── Gianna.wav
├── Henry.txt
├── Henry.wav
├── Ian.txt
├── Ian.wav
├── Jade.txt
├── Jade.wav
├── Jade_Layla.txt
├── Jade_Layla.wav
├── Jeremiah.txt
├── Jeremiah.wav
├── Jordan.txt
├── Jordan.wav
├── Julian.txt
├── Julian.wav
├── Julian_Thomas.txt
├── Julian_Thomas.wav
├── Layla.txt
├── Layla.wav
├── Leonardo.txt
├── Leonardo.wav
├── Leonardo_Olivia.txt
├── Leonardo_Olivia.wav
├── Michael.txt
├── Michael.wav
├── Michael_Emily.txt
├── Michael_Emily.wav
├── Miles.txt
├── Miles.wav
├── Oliver_Luna.txt
├── Oliver_Luna.wav
├── Olivia.txt
├── Olivia.wav
├── Ryan.txt
├── Ryan.wav
├── Taylor.txt
├── Taylor.wav
├── Thomas.txt
└── Thomas.wav
/.github/workflows/docker-build-push.yml:
--------------------------------------------------------------------------------
1 | name: Build and Push Docker Image to GHCR
2 |
3 | on:
4 | push:
5 | branches: [main]
6 | pull_request:
7 | branches: [main]
8 | workflow_dispatch:
9 |
10 | jobs:
11 | build-and-push:
12 | runs-on: ubuntu-latest
13 | permissions:
14 | contents: read
15 | packages: write
16 |
17 | steps:
18 | - name: Checkout repository
19 | uses: actions/checkout@v4
20 |
21 | - name: Set up Docker Buildx
22 | uses: docker/setup-buildx-action@v3
23 |
24 | - name: Log in to GitHub Container Registry
25 | uses: docker/login-action@v3
26 | with:
27 | registry: ghcr.io
28 | username: ${{ github.repository_owner }}
29 | password: ${{ secrets.GITHUB_TOKEN }}
30 |
31 | - name: Extract metadata for Docker
32 | id: meta
33 | uses: docker/metadata-action@v5
34 | with:
35 | images: ghcr.io/${{ github.repository_owner }}/dia-tts-server
36 | tags: |
37 | type=raw,value=latest,enable=${{ github.ref == format('refs/heads/{0}', 'main') || github.ref == format('refs/heads/{0}', 'master') }}
38 | type=sha,format=short
39 | - name: Build and push Docker image
40 | uses: docker/build-push-action@v5
41 | with:
42 | context: .
43 | push: ${{ github.event_name != 'pull_request' }}
44 | tags: ${{ steps.meta.outputs.tags }}
45 | labels: ${{ steps.meta.outputs.labels }}
46 | cache-from: type=gha
47 | cache-to: type=gha,mode=max
48 |
--------------------------------------------------------------------------------
/.gitignore:
--------------------------------------------------------------------------------
1 | # Ignore Python cache and compiled files
2 | *.pyc
3 | *.pyo
4 | *.pyd
5 | __pycache__/
6 | .ipynb_checkpoints/
7 |
8 | # Ignore distribution build artifacts
9 | .dist/
10 | dist/
11 | build/
12 | *.egg-info/
13 |
14 | # Ignore IDE/Editor specific files
15 | .idea/
16 | .vscode/
17 | *.swp
18 | *.swo
19 |
20 | # Ignore OS generated files
21 | .DS_Store
22 | Thumbs.db
23 |
24 | # Ignore virtual environment directories
25 | .venv/
26 | venv/
27 | */.venv/
28 | */venv/
29 | env/
30 | */env/
31 |
32 | # Ignore sensitive environment file
33 | .env
34 |
35 | # Ignore generated output and user data directories
36 | outputs/
37 | reference_audio/
38 | model_cache/ # Also good practice to ignore the model cache
39 |
40 | # Ignore test reports/coverage
41 | .coverage
42 | htmlcov/
43 | .pytest_cache/
44 |
45 | # Ignore log files
46 | *.log
47 |
--------------------------------------------------------------------------------
/Dockerfile:
--------------------------------------------------------------------------------
1 | FROM nvidia/cuda:12.8.1-runtime-ubuntu22.04
2 |
3 | # Set environment variables
4 | ENV PYTHONDONTWRITEBYTECODE=1
5 | ENV PYTHONUNBUFFERED=1
6 | ENV DEBIAN_FRONTEND=noninteractive
7 |
8 | # Install system dependencies
9 | RUN apt-get update && apt-get install -y --no-install-recommends \
10 | build-essential \
11 | libsndfile1 \
12 | ffmpeg \
13 | python3 \
14 | python3-pip \
15 | python3-dev \
16 | && apt-get clean \
17 | && rm -rf /var/lib/apt/lists/*
18 |
19 | # Set up working directory
20 | WORKDIR /app
21 |
22 | # Install Python dependencies
23 | COPY requirements.txt .
24 | RUN pip3 install --no-cache-dir -r requirements.txt
25 |
26 | # Copy application code
27 | COPY . .
28 |
29 | # Create required directories
30 | RUN mkdir -p model_cache reference_audio outputs voices
31 |
32 | # Expose the port the application will run on (default to 8003 as per config)
33 | EXPOSE 8003
34 |
35 | # Command to run the application
36 | CMD ["python3", "server.py"]
37 |
--------------------------------------------------------------------------------
/LICENSE:
--------------------------------------------------------------------------------
1 | MIT License
2 |
3 | Copyright (c) 2025 devnen
4 |
5 | Permission is hereby granted, free of charge, to any person obtaining a copy
6 | of this software and associated documentation files (the "Software"), to deal
7 | in the Software without restriction, including without limitation the rights
8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
9 | copies of the Software, and to permit persons to whom the Software is
10 | furnished to do so, subject to the following conditions:
11 |
12 | The above copyright notice and this permission notice shall be included in all
13 | copies or substantial portions of the Software.
14 |
15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
21 | SOFTWARE.
22 |
--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | # Dia TTS Server: OpenAI-Compatible API with Web UI, Large Text Handling & Built-in Voices
2 |
3 | **Self-host the powerful [Nari Labs Dia TTS model](https://github.com/nari-labs/dia) with this enhanced FastAPI server! Features an intuitive Web UI, flexible API endpoints (including OpenAI-compatible `/v1/audio/speech`), support for realistic dialogue (`[S1]`/`[S2]`), improved voice cloning, large text processing via intelligent chunking, and consistent, reproducible voices using 43 built-in ready-to-use voices and generation seeds feature.**
4 |
5 | The latest Dia-TTS-Server version now has improved speed and reduced VRAM usage. Defaults to efficient BF16 SafeTensors for reduced VRAM and faster inference, with support for original `.pth` weights. Runs accelerated on NVIDIA GPUs (CUDA) with CPU fallback.
6 |
7 | ➡️ **Announcing our new TTS project:** Explore the Chatterbox TTS Server and its features: [https://github.com/devnen/Chatterbox-TTS-Server](https://github.com/devnen/Chatterbox-TTS-Server)
8 |
9 | [](LICENSE)
10 | [](https://www.python.org/downloads/)
11 | [](https://fastapi.tiangolo.com/)
12 | [](https://github.com/huggingface/safetensors)
13 | [](https://www.docker.com/)
14 | [](#)
15 | [](https://developer.nvidia.com/cuda-zone)
16 | [](https://platform.openai.com/docs/api-reference)
17 |
18 |
19 |
20 |
21 |