Simli Deepgram AI Agent Technical Demo

Combine Text-to-Speech, Speech-to-Text and Simli's Speech-to-Video into a conversational agent.

deepgram+simli.mp4

Demo features

• Capture streaming audio using Deepgram Streaming Speech to Text.
• Natural Language responses using an OpenAI LLM.
• Text to Speech conversion using Deepgram Aura Text to Speech.
• Speech to Video avatars using Simli LipsyncStream

Quickstart

Manual

Follow these steps to get started with this starter application.

Clone the repository

Go to GitHub and clone the repository.

Install dependencies

Install the project dependencies.

npm install

Edit the config file

Copy the code from sample.env.local and create a new file called .env.local.

DEEPGRAM_STT_DOMAIN=https://api.deepgram.com
DEEPGRAM_API_KEY=YOUR-DG-API-KEY
OPENAI_API_KEY=YOUR-OPENAI-API-KEY
NEXT_PUBLIC_SIMLI_API_KEY=YOUR-SIMLI-API-KEY

1. For DEEPGRAM_API_KEY paste in the key you generated in the Deepgram console.
2. Set DEEPGRAM_STT_DOMAIN to be https://api.deepgram.com.
3. OPENAI_API_KEY should be an OpenAI API Key that can access the chat completions API.
4. SIMLI-API-KEY get your simli key from Simli

Build the application

Once running, you can access the application in your browser.

npm run build

npm start

Author

Deepgram

License

This project is licensed under the MIT license. See the LICENSE file for more info.