u2-asr
Unisound's speech recognition model for 15 languages and many Chinese dialects, served as one-shot, realtime streaming and asynchronous long-audio transcription.
01 Price
¥1per hour
U2-ASR input ¥1 per hour of audio, pay-as-you-go.
Pricing source, checked 2026-11-18
02 Languages 15
- Arabicar-SA
- Chinesezh-CN
- Englishen-US
- Frenchfr-FR
- Germande-DE
- Indonesianid-ID
- Italianit-IT
- Japaneseja-JP
- Koreanko-KR
- Portuguesept-BR
- Russianru-RU
- Spanishes-MX
- Thaith-TH
- Turkishtr-TR
- Vietnamesevi-VN
03 Features 5 of 11 listed
- Word timestamps
- Speaker diarization
- Punctuation
- Profanity filternot listed
- Custom vocabulary
- Language detection
- Translationnot listed
- Sentimentnot listed
- PII redactionnot listed
- Summarizationnot listed
- Topic detectionnot listed
"Not listed" means the provider's data doesn't mention it, not that the model lacks it.
04 Get this record
curl https://voicedex.dev/v1/providers/unisound/models/u2-asr
Free, no key needed. Use model id u2-asr with Unisound (云知声)'s own API. API reference.