https://github.com/murabcd/voice-agent
Realtime AI Voice Agent built with Next.js and OpenAI.
https://github.com/murabcd/voice-agent
jinaai nextjs openai react realtime voice
Last synced: 12 months ago
JSON representation
Realtime AI Voice Agent built with Next.js and OpenAI.
- Host: GitHub
- URL: https://github.com/murabcd/voice-agent
- Owner: murabcd
- Created: 2025-04-06T16:12:18.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-06-16T19:16:45.000Z (about 1 year ago)
- Last Synced: 2025-06-16T19:43:14.285Z (about 1 year ago)
- Topics: jinaai, nextjs, openai, react, realtime, voice
- Language: TypeScript
- Homepage: https://voice-oss.vercel.app
- Size: 1.33 MB
- Stars: 3
- Watchers: 1
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
An Open-source Realtime AI Voice Agent Built With Next.js, and OpenAI.
- Sequential agent handoffs according to a defined agent graph (inspiration from [OpenAI Swarm](https://github.com/openai/swarm))
- Background escalation for high-stakes decisions
- Prompting models to follow a state machine, for example to accurately collect things like names and phone numbers with confirmation character by character to authenticate a user
Features ·
Model Provider ·
Deploy Your Own ·
Running locally
## Features
- [Next.js](https://nextjs.org) App Router
- Advanced routing for seamless navigation and performance
- React Server Components (RSCs) for server-side rendering and increased performance
- [OpenAI](https://openai.com/) Integration
- Leverages OpenAI's powerful models for chat generation.
- Direct API calls for text generation and other AI features.
- Web search capabilities through OpenAI's Response API for real-time information retrieval
- [Jina Reader](https://jina.ai/) Integration
- Advanced web scraping capabilities for extracting structured data from websites
- Enhances the AI's ability to process and understand web content
- [Shadcn/ui](https://ui.shadcn.com)
- Styling with [Tailwind CSS](https://tailwindcss.com)
- Component primitives from [Radix UI](https://radix-ui.com) for accessibility and flexibility
## Model Provider
This app utilizes the [OpenAI API](https://openai.com/) for its AI capabilities. It is configured to use OpenAI models for generating responses.
- Realtime Model (`gpt-4o-mini-realtime-preview`): Higher quality conversational model with higher latency
- Realtime Mini Model (`gpt-4o-realtime-preview`): Optimized for low-latency conversational responses
- Chat Model (`gpt-4.1`): General purpose GPT-4.1 model
- Chat Mini Model (`gpt-4.1-mini`): Smaller variant of GPT-4.1
- Transcribe Model (`gpt-4o-transcribe`): Optimized for speech-to-text transcription
- Transcribe Mini Model (`gpt-4o-mini-transcribe`): Optimized for low-latency speech-to-text transcription
## Deploy Your Own
You can deploy your own version of the Voice to Vercel with one click:
[](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2Fmuradpm%2Fvoice&env=OPENAI_API_KEY,JINA_API_KEY&envDescription=Learn%20more%20about%20how%20to%20get%20the%20API%20Keys%20for%20the%20application&envLink=https%3A%2F%2Fgithub.com%2Fmuradpm%2Fopenchat%2Fblob%2Fmain%2F.env.example&demo-title=Voice&demo-description=An%20Open-source%20Realtime%20AI%20Voice%20Agent%20Built%20With%20Next.js&demo-url=https%3A%2F%2Fvoice-oss.vercel.app)
## Running locally
You will need to use the environment variables [defined in `.env.example`](.env.example) to run Voice. It's recommended you use [Vercel Environment Variables](https://vercel.com/docs/projects/environment-variables) for this, but a `.env` file is all that is necessary.
> Note: You should not commit your `.env` file or it will expose secrets that will allow others to control access to your various OpenAI and authentication provider accounts.
1. Install Vercel CLI: `npm i -g vercel`
2. Link local instance with Vercel and GitHub accounts (creates `.vercel` directory): `vercel link`
3. Download your environment variables: `vercel env pull`
```bash
bun install
bun dev
```
Your app should now be running on [localhost:3000](http://localhost:3000/).
