feisuo/ASTRA.ai

A lightning-fast workflow builder, it supports multimodal interaction, highly customizable extensions, and is intuitive to use even without any coding knowledge.

Lightning Fast   •   Multimodal Interactive   •   Highly Customizable

Voice agent: Astra

Voice agent: Astra

We showcase an impressive voice agent called Astra, powered by TEN, demonstrating its ability to create intuitive and seamless conversational interactions.

How to build voice agent locally

Prerequisites

• Keys
  • Agora App ID and App Certificate(read here on how)
  • Azure's speech-to-text and text-to-speech API keys
  • OpenAI API key
• Downloads
  • Docker / Docker Compose
  • Node.js(LTS) v18

Docker setting on apple silicon

You will need to uncheck "Use Rosetta for x86_64/amd64 emulation on apple silicon" option for Docker if you are on Apple Silicon, otherwise the server is not gonna work.

1. Prepare config files

In the root of the project, create these files from the examples. They will be used to store information for Docker Compose later.

# Create property.json from the example
cp ./agents/property.json.example ./agents/property.json

# Create .env from the example
cp ./.env.example ./.env

2. Setup API keys & Environment variables in .env file

Open the .env file and fill in the keys and regions. This is also where you can choose to use any different extensions:

# Agora App ID and Agora App Certificate
# required: this variable must be set
AGORA_APP_ID=
AGORA_APP_CERTIFICATE=

# Extension: agora_rtc
# Azure STT key and region
AZURE_STT_KEY=
AZURE_STT_REGION=

# Extension: azure_tts
# Azure TTS key and region
AZURE_TTS_KEY=
AZURE_TTS_REGION=

# Extension: openai_chatgpt
# OpenAI API key
OPENAI_API_KEY=

3. Start agent builder toolkit containers

In the same directory, run the docker command to compose containers:

# Execute docker compose up to start the services
docker compose up

4. Build your agent and start server

Open up a separate terminal window, build the agent and start the server:

# Enter container to build agent
docker exec -it astra_agents_dev bash
make build

# Run server on port 8080
make run-server

5. Verify your voice agent 🎉

You can open localhost:3000 in your browser to test your own agent, or open localhost:3001 in your browser to build your workflow by Graph Designer.

TEN Service

Discover More

Now that you’ve created your first AI agent, the creativity doesn’t stop here. To develop more amazing agents, you’ll need an advanced understanding of how the TEN works under the hood. Please refer to the TEN service documentation .

Stay Tuned

Before we dive further, be sure to star our repository and get instant notifications for all new releases!

Join Community

• Discord: Ideal for sharing your applications and engaging with the community.
• Github Discussion: Perfect for providing feedback and asking questions.
• GitHub Issues: Best for reporting bugs and proposing new features. Refer to our contribution guidelines for more details.
• X (formerly Twitter): Great for sharing your agents and interacting with the community.

Code Contributors

Contribution Guidelines

Contributions are welcome! Please read the contribution guidelines first.

License

This project is licensed under the Apache 2.0 License - see the LICENSE file for details.