As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/seedrealtime/

# SeedRealtime (Doubao realtime audio-visual model)

ByteDance, Seed family. Status: current. Type: speech and audio. Released: 2026-08-05.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Web app (Doubao / Dola) |  |  | https://dola.com/chat |
| BytePlus Playground |  |  | https://ai.byteplus.com/en/playground |

## Pricing

- Price not published.
- Last checked: not recorded

## Specs

- Input: audio, video, text
- Output: audio, text
- Context window: not published
- Max output: not published
- Open weights: no
- Licence: proprietary

## Where it stands

- Newer speech and audio models in the registry since its release: 37. The 5 newest:
  - NVIDIA Nemotron 3.5 Transcribe (30B-A4B) (2026-10-28) https://postcutoff.com/m/nemotron-3-5-transcribe/
  - Hy-SimulMT-30B-A3B (2026-10-22) https://postcutoff.com/m/hy-simulmt-30b-a3b/
  - Eleven Realtime v1 Max / Mini (2026-10-20) https://postcutoff.com/m/eleven-realtime-v1-max/
  - Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3) (2026-10-20) https://postcutoff.com/m/voxtral-mini-transcribe-3/
  - Voxtral Small Transcribe 3 (2026-10-20) https://postcutoff.com/m/voxtral-small-transcribe-3/
- Before it from ByteDance: Seed Audio 1.0 (2026-07-20) https://postcutoff.com/m/seed-audio-1-0/
- Closed weights.

## What stands out

- Native audio-visual full-duplex LLM: Single end-to-end model perceives continuous audio, video and text streams while listening and speaking (no ASR/VLM/TTS cascade); resolves homophones from visual context and temporal references to what it sees. Source: https://seed.bytedance.com/en/blog/seedrealtime-audio-visual-full-duplex-llm-released-toward-omni-modal-natural-interaction
- Proactive turn-taking: ByteDance says it halves audio-visual conversational pacing problems vs cascaded systems (fewer cut-offs, slow replies, false triggers) and can speak up proactively. Source: https://seed.bytedance.com/en/SeedRealtime

## Notes

Deployed at scale in the Doubao app (Dola internationally). No public API model id, pricing or benchmark numbers published; Volcengine offers a separate Doubao end-to-end realtime dialogue API (/api/v3/realtime/dialogue) whose relation to SeedRealtime is unverified. Some press calls it the first model to watch, listen and speak simultaneously; not claimed by ByteDance, and Gemini Live / GPT-Realtime already accepted video.

Sources: https://seed.bytedance.com/en/SeedRealtime · https://seed.bytedance.com/en/blog/seedrealtime-audio-visual-full-duplex-llm-released-toward-omni-modal-natural-interaction · https://technode.com/2026/08/05/bytedance-launches-seedrealtime-full-duplex-audio-video-model/

Model page: https://postcutoff.com/m/seedrealtime/