LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.
MooER: Moore-threads Open Omni model for speech-to-speech intERaction. MooER-omni includes a series of end-to-end speech interaction models along with training and inference code, covering but not limited to end-to-end speech interaction, end-to-end speech translation and speech recognition.
a fully open-source implementation of a GPT-4o-like speech-to-speech video understanding model.
[CVPR 2025] OmniMMI: A Comprehensive Multi-modal Interaction Benchmark in Streaming Video Contexts
ε ¨εε·₯θ―ι³ε©ζοΌθΎΉε¬θΎΉθ―΄γζζγδ»»ε‘ε§ζ΄ΎδΈε·₯ε ·ζ§θ‘γFull-duplex voice agent with barge-in, streaming audio, and async thinking. DuplexOmni (arXiv:2606.09186).
web-based voice-controlled media player, designed to run in any modern browser (Chrome/Edge recommended).
Ergonomic, hands-free ambient speech-to-text with voice commands, wake-word, VAD, feedback, realtime partials and NATS
To associate your repository with the speech-interaction topic, visit your repo's landing page and select "manage topics."