Seed ASR 2.0 API by ByteDance
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.
Seed ASR 2.0 (Recording-File Recognition)
Seed ASR 2.0 (BytePlus Seed Speech) transcribes an audio file into text. Built on an audio-conditioned LLM, it delivers state-of-the-art accuracy with punctuation, inverse text normalization, sentence segmentation and speaker diarization.
🌟 Key Features
🗣 High-Accuracy Transcription
LLM-based recognition with deep context understanding — strong on dynamic, real-world speech.
🌍 51 Languages
Chinese, English and domestic dialects (Cantonese, Shanghainese, Sichuanese, etc.) plus 48 more including Japanese, Spanish, Portuguese, Arabic, Hindi.
🎯 Rich Output
Punctuation, ITN (number normalization), semantic smoothing, per-sentence timestamps, and speaker diarization (up to 10 speakers).
📻 Far-Field Optimized
~50% error-rate reduction on far-field test sets (speakers, TVs, glasses).
⚙️ Parameters
| Parameter | Required | Description |
|---|---|---|
audio_url* | ✅ | Audio file URL or Base64. Formats: wav/mp3/ogg/raw. |
format | ⬜ | Audio format: mp3 (default) / wav / ogg / raw. |
language | ⬜ | Language code (e.g. en-US, yue-CN); empty = auto (CN/EN/dialects). 51 languages. |
enable_itn | ⬜ | Inverse text normalization. Default true. |
enable_punc | ⬜ | Add punctuation. Default false. |
enable_ddc | ⬜ | Semantic smoothing. Default false. |
enable_speaker_info | ⬜ | Speaker diarization. Default false. |
show_utterances | ⬜ | Per-sentence segments + timestamps. Default false. |
📤 Output
outputs[0] contains the recognized transcript text.
🎯 Use Cases
- Meeting & Interview Transcription — turn recordings into searchable text.
- Media Subtitling — transcribe podcasts/videos with timestamps.
- Voice Analytics — call-center QA, speaker diarization.
- Multilingual Content — transcribe across 51 languages.
