Back: Catalog

Vision-Agents

Vision-Agents is a Python library designed to develop multi-module AI assistants with real-time video and audio processing capabilities. Using stream end network infrastructure, it offers low latency and combines object recognition models such as YOLO, Roboflow, and large language models such as OpenAI, Gemini, Claude. Multiple platforms such as React, Android, iOS, Flutter, and Unity provide SDK support.

VI

Vision-Agents

80

GetStream · Voice & Text-to-Speech

STARS8.2K
FORKS698
COMMITS0
CONTRIBUTORS0
VERSIONv0.6.9
UPDATEDtoday
PythonVideo AIReal-TimeWebRTCApache-2.0

Common commercial products in this category: ElevenLabs, Amazon Polly, Google Cloud Text-to-Speech

What can it do?
  • By combining YOLO and Gemini models, you can develop AI assistants that perform real-time video analysis.
  • Using the stream end network, you can get audio and video latency under 30 milliseconds.
  • With Twilio or Telnyx integration, you can create phone calls with a bidirectional audio stream.
Website GitHub

My note

Alternative pages

ElevenLabs alternativesAmazon Polly alternativesGoogle Cloud Text-to-Speech alternatives

More in: Voice & Text-to-Speech