https://github.com/deepgram-starters/node-live-text-to-speech
Get started using Deepgram's Live Text-to-Speech with this Node demo app
https://github.com/deepgram-starters/node-live-text-to-speech
deepgram live real-time text-to-speech tts websockets
Last synced: 4 months ago
JSON representation
Get started using Deepgram's Live Text-to-Speech with this Node demo app
- Host: GitHub
- URL: https://github.com/deepgram-starters/node-live-text-to-speech
- Owner: deepgram-starters
- License: mit
- Created: 2024-08-29T19:27:27.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2025-12-16T23:25:49.000Z (6 months ago)
- Last Synced: 2025-12-19T09:00:36.942Z (6 months ago)
- Topics: deepgram, live, real-time, text-to-speech, tts, websockets
- Language: JavaScript
- Homepage: https://community.deepgram.com/
- Size: 194 KB
- Stars: 3
- Watchers: 2
- Forks: 3
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Code of conduct: CODE_OF_CONDUCT.md
Awesome Lists containing this project
README
# Node Live Text-to-Speech Starter
Live text-to-speech demo using Deepgram's Speak API with Node.js backend and web frontend.
## Sign-up to Deepgram
Before you start, it's essential to generate a Deepgram API key to use in this project. [Sign-up now for Deepgram and create an API key](https://console.deepgram.com/signup?jump=keys).
## Prerequisites
- [Deepgram API Key]((https://console.deepgram.com/signup?jump=keys)) (sign up for free)
- Node.js 24 and pnpm 10+
**Note:** This project uses strict supply chain security measures. npm and yarn will NOT work. See [SECURITY.md](SECURITY.md) for details.
## Quickstart
Follow these steps to get started with this starter application.
1. Clone the repository
Go to GitHub and [clone the repository](https://github.com/deepgram-starters/node-live-text-to-speech).
1. Install dependencies
Install the project dependencies:
```bash
# Option 1: Use the helper script (recommended)
pnpm run install:all
# Option 2: Manual two-step install
pnpm install
cd frontend && pnpm install && cd ..
```
**Note:** Due to security settings (`ignore-scripts=true`), frontend dependencies must be installed separately. The `install:all` script handles both steps.
2. **Set your API key**
Create a `.env` file:
```bash
DEEPGRAM_API_KEY=your_api_key_here
```
3. **Run the app**
**Development mode** (with hot reload):
```bash
pnpm dev
```
**Production mode** (build and serve)
```bash
# Build the frontend
pnpm build
# Start the production server
pnpm start
```
### 🌐 Open the App
[http://localhost:3000](http://localhost:3000)
## How It Works
This application:
1. Accepts live text input via WebSocket connection
2. Send the text to convert to audio to Deepgram's live Text-to-Speech API
3. Returns real-time Text-to-Speech audio results to the client
4. Audio starts playing after ALL chunks arrive and Flushed message received
## Getting Help
- [Open an issue in this repository](https://github.com/deepgram-starters/node-live-text-to-speech/issues/new)
- [Join the Deepgram Github Discussions Community](https://github.com/orgs/deepgram/discussions)
- [Join the Deepgram Discord Community](https://discord.gg/xWRaCDBtW4)
## Contributing
See our [Contributing Guidelines](./CONTRIBUTING.md) to learn about contributing to this project.
## Code of Conduct
This project follows the [Deepgram Code of Conduct](./CODE_OF_CONDUCT.md).
## Security
For security policy and procedures, see our [Security Policy](./SECURITY.md).
## License
MIT - See [LICENSE](./LICENSE)