SeedRealtime

SeedRealtime jointly understands sound, vision, and temporal cues for natural, full-duplex interaction as you watch, listen, and speak.

Capabilities

Infrastructure
Streaming

Details

Provider ByteDance Seed
Creator bytedance
Family—
License—
Statusactive
Typechat
Input modalitiestext, image
Output modalitiestext
Open weight—
Parameters—
Architecture—
Context window—
Max input—
Max output—
Reasoning tokens—
Knowledge cutoff—
Release date—
Sourceofficial

Endpoints

Chat CompletionsPOST
Generate chat responses with messageshttps://console.volcengine.com/ark/v1/chat/completions

API

GET/v1/models/bytedance/seedrealtime

SeedRealtime

SeedRealtime jointly understands sound, vision, and temporal cues for natural, full-duplex interaction as you watch, listen, and speak.

Changes · 3 entries
seedrealtimecreateca7a400Nov 2, 2026, 03:02 AM
seedrealtimeupdate118451aSep 24, 2026, 07:08 AM
descriptionAs a native audio-visual full-duplex LLM, SeedRealtime ca...→SeedRealtime jointly understands sound, vision, and tempo...
seedrealtimecreate19c9fe3Aug 5, 2026, 03:04 PM