kristofferv98/openai-voicestream

OpenAI VoiceStream: Real-time text-to-speech library for processing text and token streams using the OpenAI API. Supports multiple voices and thread-safe audio generation.

30
/ 100
Emerging

This tool helps you turn written text, even as it's being generated, into natural-sounding speech in real-time. You input text, either all at once or in small segments, and it outputs clear audio using various voices. It's designed for developers building applications where immediate voice output is crucial, like AI assistants or interactive voice responses.

No commits in the last 6 months. Available on PyPI.

Use this if you are a developer building an application that needs to vocalize text as it's being created, such as a chatbot responding in real-time or a system narrating streaming information.

Not ideal if you need fine-grained control over audio properties like speed, pitch, or specific emotional tones beyond selecting a pre-defined voice.

real-time-audio text-to-speech-development AI-assistant-development streaming-audio voice-user-interface
No License Stale 6m
Maintenance 0 / 25
Adoption 4 / 25
Maturity 17 / 25
Community 9 / 25

How are scores calculated?

Stars

7

Forks

1

Language

Python

License

Last pushed

Jun 01, 2024

Commits (30d)

0

Dependencies

2

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/kristofferv98/openai-voicestream"

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