Post-Cutoff
Search For AI agents

ByteDanceSeed familyCurrentSpeech and audioReleased 20 Jul 2026

Seed Audio 1.0

PricePrice not published

Where it stands

42newer speech and audio models since its release

The 5 newest are listed. All speech and audio models

After it from ByteDance
SeedRealtime (Doubao realtime audio-visual model)5 Aug 2026
Weights
Closed weights.

How to call it

Where to use Seed Audio 1.0.

Providers, model ids, endpoints and docs for Seed Audio 1.0
ProviderModel idEndpointDocs
BytePlus (Seed Speech console) console.byteplus.com

Pricing

Price not published.

No price source linked.

Specs

Input
Text and audio
Output
Audio
Context window
Not published
Max output
Not published
Open weights
No
Licence
Proprietary
Released
20 July 2026
Status
Current
Type
Speech and audio

What stands out

What its maker marketed at launch, and what people found later, each with its source.

  • Unified speech + SFX + ambience generation

    Jointly models voice, sound effects and ambience in one framework for film-grade audio; multi-character dialogue with prompt-level timing control at 100 ms precision; up to 2 min per generation with continuation.

    Source: seed.bytedance.com

  • 20+ languages

    Including zh, en, ja, ko, es, id, de, fr, th, vi; most languages MOS > 4.0 in ByteDance’s evaluation.

    Source: seed.bytedance.com

Notes

API model id and pricing not found. Related ByteDance speech stack: Seed-TTS 2.0 / Doubao TTS 2.0 (Oct 2025), Doubao-Seed-ASR-2.0, Seed LiveInterpret 2.0 (2025-07-24, zh<->en simultaneous interpretation with voice cloning, ~2.5-3 s lag; see entry ByteDance’s LiveInterpret 2.0 interprets Chinese-English simultaneously in your own voice) on Volcengine/BytePlus. Comparable: Qwen-Audio-3.1-TTS-Next, StepAudio 3 Gen.

Sources: https://seed.bytedance.com/en/seedaudio1_0 · https://seed.bytedance.com/en/blog/from-speech-to-audio-creation-introducing-the-seed-audio-1-0-audio-creation-model