leonardofmed/stt-chat-tts

This is a Python project that uses different modules to capture audio from a microphone, transcribe it into text using Mozilla's DeepSpeech engine, use a chatbot to generate a response based on the text, and generate speech output from the response using Google Text-to-Speech (gTTS)

26
/ 100
Experimental

This project helps you have a spoken conversation with an AI chatbot. You speak into your microphone, and your words are transcribed into text. The chatbot generates a text response, which is then spoken back to you. This is for anyone who wants to interact with an AI conversationally, without typing.

No commits in the last 6 months.

Use this if you want to experiment with voice-controlled AI conversations or build simple voice-enabled interactive systems.

Not ideal if you need highly accurate, real-time speech transcription for complex, critical applications or if you require advanced conversation flow management.

voice-interaction AI-chat personal-assistant prototyping voice-user-interface
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 13 / 25

How are scores calculated?

Stars

9

Forks

2

Language

Python

License

Last pushed

Feb 28, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/leonardofmed/stt-chat-tts"

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