SuperAPI AI Directory
Partner with us中文AI newsFavorites
DirectoryNews and tutorials

WorldCupVoice - Open-Source AI Real-Time Sports Commentary System

Author: AI小集 · Original source: AI工具集

What is WorldCupVoice

WorldCupVoice is an open-source AI real-time sports commentary system. By connecting to Agora RTC live streams, a vision model analyzes the match footage and generates real-time voice commentary, which is sent back to the live room for viewers to listen to in sync. The system supports OpenAI TTS,ElevenLabs and Fish Audio multiple voice engines, and can be configured with multilingual commentary styles such as English, French, and Chinese. The system is designed specifically for sports events such as the World Cup, while also accommodating the accessible viewing needs of visually impaired users, providing information such as pitch spatial details that traditional commentary often overlooks.

WorldCupVoice

Main Features of WorldCupVoice

  • Real-Time AI Commentary: Samples video frames from Agora RTC live streams, analyzes the match footage with a vision model, generates real-time voice commentary, and sends it back to the live room.
  • Multi-Voice Engine Support: Compatible with OpenAI TTS, ElevenLabs, and Fish Audio.
  • Multilingual Commentary: Supports multiple languages such as English, French, and Chinese, and can be configured with commentary styles from different countries.
  • Live Stream Access: Via RTMP push → Agora Media Gateway → RTC channel, compatible with multiple sources such as OBS, local video, and cloud push.
  • Browser Viewing Interface: A Next.js-based frontend that simultaneously plays live video, AI commentary audio, real-time subtitles, and commentator status monitoring.
  • Cost Control Mechanism: Explicit Start/Stop AI control, viewer heartbeat detection, and hard session timeout prevent unlimited consumption of AI resources.
  • Visually Impaired Assistance Mode: Provides pitch-level spatial details, compensating for information that traditional human commentary often overlooks.
Dig Into GitHub

Follow WeChat and reply “Open Source” to join theAI Open-Source Project Communication Group

How to Use WorldCupVoice

  • Environment Preparation: Configure Agora App ID/Certificate, OpenAI API Key, and generate the backend secret key.
  • Frontend Startup：pnpm install → Configure .env.local → pnpm dev。
  • Backend Startup：cd server → Create a Python virtual environment → pip install → Configure the TTS provider → uvicorn app.main:app。
  • Push Setup: Generate an RTMP push key via the Agora Media Gateway REST API, and push the stream using OBS or local ffmpeg.
  • Start Commentary: Enter the live room in the browser and click “Start AI” to launch the AI commentator.

Core Advantages of WorldCupVoice

  • Real-Time Performance: The AI and viewers watch the same RTC stream, and commentary latency is controllable.
  • Accessibility Design: Provides visually impaired users with spatial detail information that traditional commentary cannot cover.
  • Multiple Voice Styles: Supports professional sports commentator styles (ElevenLabs), Chinese meme commentary (Fish Audio), and tactical analysis styles.
  • Controllable Cost: Session-level start/stop control + heartbeat mechanism + hard timeout avoid wasting AI resources.
  • Open Source and Extensible: MIT license, supports injecting custom match data into the AI context.

WorldCupVoice Project Address

  • GitHub Repository：https://github.com/zicojiao/worldcupvoice

Comparison of WorldCupVoice with Similar Competitors

Comparison Dimension WorldCupVoice WSC Sports
Product Positioning Open-source real-time AI sports commentary system Enterprise-grade AI sports content automation platform
Core Features Watch RTC live streams in real time and generate AI voice commentary Automatically identify highlight moments in matches and generate highlights, short videos, and social media content
Real-time Capability Real-time live commentary, listeners hear it in sync with the audience Analyzes live streams in real time, but is mainly used to automatically generate content after or during matches
Open-source Nature Open-sourced under the MIT license, self-hostable Closed-source SaaS platform, enterprise subscription model
Deployment Method Frontend on Vercel + backend on Railway, self-hosted Cloud SaaS, API integration
Voice Capabilities Supports multiple engines including OpenAI TTS, ElevenLabs, and Fish Audio Built-in AI dubbing and multilingual support
Accessibility Design Designed specifically for visually impaired users, providing spatial details of the pitch General-purpose sports content generation, not specifically targeted at the visually impaired

WorldCupVoice Use Cases

  • World Cup/Football Match Live Broadcasts: Add an AI commentary channel to live streaming platforms, offering choices of multiple languages and styles.
  • Sports Viewing for the Visually Impaired: Provide blind or low-vision users with detailed commentary on spatial information of the pitch.
  • Live Broadcasts of Niche Events: Provide automated commentary for lower-tier leagues and campus matches that lack professional commentary resources.
  • Multilingual International Events: Output AI commentary in multiple languages such as Chinese/English/French simultaneously from the same match stream.
  • Esports Commentary: Extend to real-time AI tactical commentary for esports matches such as LOL and CS2.