Blog/Audio
Aug 5, 2026
SeedRealtime Audio-Visual Full-Duplex LLM Released: Toward Omni-Modal Natural InteractionAs a native audio-visual full-duplex LLM, SeedRealtime can jointly understand audio, visual, and temporal information, accurately identify the interaction target and user intent, delivering a brand-new "watch, listen, and speak" experience.
Jul 20, 2026
From Speech to Audio Creation | Introducing the Seed Audio 1.0 Audio Creation ModelA unified framework for joint modeling of voice, sound effects, ambient sound, and other audio elements.
Apr 9, 2026
Introducing Seed Full-Duplex Speech LLM: Attentive Listening, Robust Interference Suppression, Enabling More Natural InteractionAs a native full-duplex speech LLM, it achieves high-precision interference suppression and adaptive endpoint detection.
Jul 24, 2025
Seed LiveInterpret 2.0 Released: An End-to-End Simultaneous Interpretation Model Featuring Ultra-High Accuracy Close to Human Interpreters, Low Latency of 3 Seconds, and Real-Time Voice CloningSeed LiveInterpret 2.0 achieves SOTA quality in both Chinese-to-English and English-to-Chinese interpretation with ultra-low latency.
Jan 20, 2025
Doubao Realtime Voice Model Is Available Upon Release! High EQ and IQA native approach integrates speech and text modes to truly implement an end-to-end model of understanding and generation.