Ejb503/ai-voice-generation

Experience the power of AI with this free AI voice generator demo. Utilizing Deepgram and Groq, we transform text into voice seamlessly. This repository contains a simple and efficient implementation using NextJS. Dive into the world of AI voice generation for free with our comprehensive demo. Contributions welcome.

35
/ 100
Emerging

Implements a full voice chat pipeline—speech recognition via WebSpeechRecognition API, LLM inference through Groq's Llama 3, and TTS via Deepgram—all streamed end-to-end in the browser. The architecture chains voice-to-text transcription directly into prompt-based LLM processing, enabling customization through system prompts and context manipulation. Built on NextJS with Express backend, it serves as a cost-effective alternative to proprietary voice APIs, with notes on swapping components (e.g., Whisper for SpeechRecognition) for production stability.

No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

37

Forks

5

Language

TypeScript

License

MIT

Category

text-to-speech

Last pushed

Jun 12, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/Ejb503/ai-voice-generation"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.