R_REDDYX.XYZ
AIPython★ 324⑂ 30 forksApache-2.0

adventists-ai/sophon-realtime

Open Full-Duplex Voice Models

Sophon-Realtime v1 provides open full-duplex voice models that understand and express tone. Tag and Flash run on one GPU via vLLM-Omni; end-to-end version in preview.

// KEY FEATURES

  • Runs Tag and Flash voice models on one GPU using vLLM-Omni
  • Full-duplex models that hear tone and speak with tone
  • End-to-end real-time voice model in preview release
#full-duplex#open-source#paralinguistics#realtime#speech#speech-to-speech#vllm#voice-assistant
Open on GitHub →

New repositories every 30 minutes

REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.

Join on Telegram
← Full catalog·Full index

// SIMILAR REPOSITORIES

POLYMARKET AI TRADING - PREDICTION BOT★ 324OPENCLAW ASSISTANT - VOICE ASSISTANT ANDROID★ 324SCRIBE.JS - OCR IN JAVASCRIPT★ 324OPENCODE BAR: Token Track★ 324AI Reconnaissance and Reports★ 324GOLDENEYE PC PORT★ 324

← FULL CATALOG

adventists-ai/sophon-realtime — Open Full-Duplex Voice Models