Skip to main content
Radar

Keep up with the models you depend on. Follow price changes, retirements, and API updates.Follow the models you depend on.

Follow model changes
Official provider results

SeedRealtime launch notes

ByteDance Seed’s August 5, 2026 announcement describes an end-to-end audio-visual full-duplex model and reports a halving of conversational pacing issues versus cascaded pipelines.

Source snapshots refreshed
Five measurement lanesVOICE / S2S

Reasoning, task completion, conversation dynamics, experience, and latency stay separate.

Back to directory

Benchmark profile

Scope
Relative conversational-pacing claim versus cascaded ASR–LLM–TTS systems and architecture disclosures
Primary metric
Documented capabilities (no scored benchmark)
Owner
ByteDance Seed
Available evidence
Relative claim only

What it measures

Conversation dynamics
Can it handle turns, interruptions, ambiguity, and state?

Available results

Conversational pacing issues
Halved vs cascaded systems
Provider-reported

Fewer interruptions, false triggers, and latency spikes in single-turn use.

Modalities
Audio, video, and text streams
Documented

Perception, understanding, decision, and response in one model.

Interpretation limit

Provider claim without a published benchmark table or competitor values.