supershaneski/openai-whisper-talk

openai-whisper-talk is a sample voice conversation application powered by OpenAI technologies such as Whisper, Completions, Embeddings, and the latest Text-to-Speech. The application is built using Nuxt, a Javascript framework based on Vue.js.

47
/ 100
Emerging

Implements Schedule Management and Long-Term Memory by combining voice I/O with semantic search—audio is preprocessed to remove silence before Whisper transcription, then routed through Chat Completions with function-calling to enable structured tasks like calendar updates and persistent knowledge storage via embeddings. The backend uses ffmpeg to filter audio files before API submission, preventing Whisper hallucinations, while Nuxt provides real-time bidirectional voice interaction across customizable chatbot personalities.

163 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

163

Forks

38

Language

JavaScript

License

MIT

Last pushed

Jan 29, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/supershaneski/openai-whisper-talk"

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