Seed ASR 2.0 — Reelina AI 사운드
Audio container format.
Optional language code. Leave empty to auto-recognize Chinese/English/dialects. Or set a code, e.g. en-US, zh-CN, yue-CN, ja-JP, es-MX (51 languages supported).
enable itn
Inverse text normalization (e.g. 'one hundred' -> '100').
enable punc
Add punctuation to the transcript.
enable ddc
Semantic smoothing (remove fillers/repeats).
enable speaker info
Speaker diarization (<=10 speakers).
show utterances
Return per-sentence segments with timestamps.
About Seed ASR 2.0
BytePlus Seed Speech recording-file recognition (ASR 2.0): transcribe an audio file to text with punctuation, ITN, sentence segmentation, speaker diarization, and 51-language support.
Specifications
| Provider | ByteDance |
|---|---|
| Type | Audio generation |
| Cost per run | 1 credits |
| Input | Text prompt |
Alternatives to Seed ASR 2.0
Models in this workspace that do the same job, closest in price first. Your credit balance works across all of them.
Frequently asked questions
- What is Seed ASR 2.0?
- BytePlus Seed Speech recording-file recognition (ASR 2.0): transcribe an audio file to text with punctuation, ITN, sentence segmentation, speaker diarization, and 51-language support.
- How much does Seed ASR 2.0 cost?
- Seed ASR 2.0 costs 1 credits per run, deducted from your Reelina balance. The exact cost is shown before you press Generate, and one balance covers every model — there is no separate subscription per model.
- What do I need to use Seed ASR 2.0?
- A text prompt describing what you want. No upload needed.
- Can I use the results commercially?
- Your generations are yours to use, subject to our terms and acceptable use policy. For anything business-critical, check the licence of the specific model you pick.
- How long are my files kept?
- 업로드한 파일은 결과물을 생성하는 데에만 사용됩니다. 생성물은 기본적으로 비공개이며, 생성된 지 일주일 후 모두 삭제됩니다.
Looking for something else? Browse every model.