SeedRealtime

ByteDance · 2026 · Speech AI · China

A to Z

A · App: Yes
B · Built By: ByteDance
C · CEO & Politics: Liang Rubo — Not publicly documented (PRC-based; operates under Chinese regulatory environment)
D · Date: 2026
E · Expertise: Beginner (app available)
F · Free Tier: Yes
G · Generates: Text only
H · Deployment: Cloud (free in the Doubao app, 300M+ users)
I · Inputs: Text
J · Jurisdiction: China
K · Key Staffers: Liang Rubo (CEO)
L · Languages: Chinese-primary
M · Model Type: Speech AI
N · Safety Issues: None reported
O · Open Source: Proprietary
P · Pricing: [UNKNOWN]
Q · AIDb Rating: 8/10 · AIDb v2.0 (curated): Capability 8/10 · Currency 10/10 · Access 7/10 · Significance 7/10 → 8.10
R · What Makes It Special: Native audio-visual full-duplex LLM replacing cascaded ASR-VLM-TTS pipelines: a single end-to-end model that listens, watches and speaks simultaneously, with turn-taking inside the model and no external VAD; 50% fewer conversational pacing failures in human evals; ties voices to faces in noisy rooms and speaks up proactively on scene changes.
S · Stock / Status: Private ($330B+ valuation, Aug 2025 employee buyback)
T · Training Cutoff: [UNKNOWN]
U · Users: [UNKNOWN]
V · Voice Chat: Yes
W · Weights: API only
X · X Handle: @ByteDanceTalk
Y · Year Founded: [UNKNOWN]
Z · Bottom Line: Proprietary Speech AI from ByteDance, released 2026.

Data completeness 85% · Last verified 2026-08-09 · Primary source ↗

“SeedRealtime.” AIDb — The AI Database. Verified 2026-08-09. https://theaidatabase.com/m/bytedance-seedrealtime.html