This project provides a local, OpenAI-compatible text-to-speech (TTS) API using edge-tts. It emulates the OpenAI TTS endpoint (/v1/audio/speech), enabling users to generate speech from text with various voice options and playback speeds, just like the OpenAI API.
edge-tts uses Microsoft Edge's online text-to-speech service, so it is completely free.
View this project on Docker Hub
- OpenAI-Compatible Endpoint:
/v1/audio/speechwith similar request structure and behavior. - Supported Voices: Maps OpenAI voices (alloy, echo, fable, onyx, nova, shimmer) to
edge-ttsequivalents. - Flexible Formats: Supports multiple audio formats (mp3, opus, aac, flac, wav, pcm).
- Adjustable Speed: Option to modify playback speed (0.25x to 4.0x).
- Optional Direct Edge-TTS Voice Selection: Use either OpenAI voice mappings or specify any edge-tts voice directly.
- Docker (recommended): Docker and Docker Compose for containerized setup.
- Python (optional): For local development, install dependencies in
requirements.txt. - ffmpeg: Required for audio format conversion and playback speed adjustments.
- Clone the Repository:
git clone https://github.com/travisvn/openai-edge-tts.git
cd openai-edge-tts- Environment Variables: Create a
.envfile in the root directory with the following variables:
API_KEY=your_api_key_here
PORT=5050
DEFAULT_VOICE=en-US-AndrewNeural
DEFAULT_RESPONSE_FORMAT=mp3
DEFAULT_SPEED=1.0
DEFAULT_LANGUAGE=en-US
REQUIRE_API_KEY=True
Or, copy the default .env.example with the following:
cp .env.example .env- Run with Docker Compose (recommended):
docker compose up --build(Note: docker-compose is not the same as docker compose)
Run with -d to run docker compose in "detached mode", meaning it will run in the background and free up your terminal.
docker compose up -dAlternatively, run directly with Docker:
docker build -t openai-edge-tts .
docker run -p 5050:5050 --env-file .env openai-edge-ttsTo run the container in the background, add -d after the docker run command:
docker run -d -p 5050:5050 --env-file .env openai-edge-tts- Access the API: Your server will be accessible at
http://localhost:5050.
If you prefer to run this project directly with Python, follow these steps to set up a virtual environment, install dependencies, and start the server.
git clone https://github.com/travisvn/openai-edge-tts.git
cd openai-edge-ttsCreate and activate a virtual environment to isolate dependencies:
# For macOS/Linux
python3 -m venv venv
source venv/bin/activate
# For Windows
python -m venv venv
venv\Scripts\activateUse pip to install the required packages listed in requirements.txt:
pip install -r requirements.txtCreate a .env file in the root directory and set the following variables:
API_KEY=your_api_key_here
PORT=5050
DEFAULT_VOICE=en-US-AndrewNeural
DEFAULT_RESPONSE_FORMAT=mp3
DEFAULT_SPEED=1.0
DEFAULT_LANGUAGE=en-US
REQUIRE_API_KEY=True
Once configured, start the server with:
python app/server.pyThe server will start running at http://localhost:5050.
You can now interact with the API at http://localhost:5050/v1/audio/speech and other available endpoints. See the Usage section for request examples.
Generates audio from the input text. Available parameters:
Required Parameter:
- input (string): The text to be converted to audio (up to 4096 characters).
Optional Parameters:
- model (string): Set to "tts-1" or "tts-1-hd" (default:
"tts-1"). - voice (string): One of the OpenAI-compatible voices (alloy, echo, fable, onyx, nova, shimmer) or any valid
edge-ttsvoice (default:"en-US-AndrewNeural"). - response_format (string): Audio format. Options:
mp3,opus,aac,flac,wav,pcm(default:mp3). - speed (number): Playback speed (0.25 to 4.0). Default is
1.0.
Example request with curl and saving the output to an mp3 file:
curl -X POST http://localhost:5050/v1/audio/speech \
-H "Content-Type: application/json" \
-H "Authorization: Bearer your_api_key_here" \
-d '{
"input": "Hello, I am your AI assistant! Just let me know how I can help bring your ideas to life.",
"voice": "echo",
"response_format": "mp3",
"speed": 1.0
}' \
--output speech.mp3Or, to be in line with the OpenAI API endpoint parameters:
curl -X POST http://localhost:5050/v1/audio/speech \
-H "Content-Type: application/json" \
-H "Authorization: Bearer your_api_key_here" \
-d '{
"model": "tts-1",
"input": "Hello, I am your AI assistant! Just let me know how I can help bring your ideas to life.",
"voice": "alloy"
}' \
--output speech.mp3And an example of a language other than English:
curl -X POST http://localhost:5050/v1/audio/speech \
-H "Content-Type: application/json" \
-H "Authorization: Bearer your_api_key_here" \
-d '{
"model": "tts-1",
"input": "じゃあ、行く。電車の時間、調べておくよ。",
"voice": "ja-JP-KeitaNeural"
}' \
--output speech.mp3- POST/GET /v1/models: Lists available TTS models.
- POST/GET /v1/voices: Lists
edge-ttsvoices for a given language / locale. - POST/GET /v1/voices/all: Lists all
edge-ttsvoices, with language support information.
Contributions are welcome! Please fork the repository and create a pull request for any improvements.
This project is licensed under GNU General Public License v3.0 (GPL-3.0), and the acceptable use-case is intended to be personal use. For enterprise or non-personal use of openai-edge-tts, contact me at [email protected]
Open up the Admin Panel and go to Settings -> Audio
Below, you can see a screenshot of the correct configuration for using this project to substitute the OpenAI endpoint
Note
View the official docs for Open WebUI integration with OpenAI Edge TTS
In version 1.6.8, AnythingLLM added support for "generic OpenAI TTS providers" — meaning we can use this project as the TTS provider in AnythingLLM
Open up settings and go to Voice & Speech (Under AI Providers)
Below, you can see a screenshot of the correct configuration for using this project to substitute the OpenAI endpoint
your_api_key_herenever needs to be replaced — No "real" API key is required. Use whichever string you'd like.- The quickest way to get this up and running is to install docker and run the command below:
docker run -d -p 5050:5050 -e API_KEY=your_api_key_here -e PORT=5050 travisvn/openai-edge-tts:latest