volc.seedasr.sauc.duration
Large-model streaming speech recognition over WebSocket, in bidirectional (word-by-word) and sentence-level streaming modes.
01 Price
¥1per hour
Free tier: 20 hours on sign-up.
¥1/hour pay-as-you-go. Prepaid packs (1 year): 30 h ¥28, 1,000 h ¥900 (¥0.9/h), 10,000 h ¥8,800, 100,000 h ¥85,000, 300,000 h ¥240,000 (¥0.8/h). Concurrency-billed variant volc.seedasr.sauc.concurrent: ¥500 per concurrent stream per month, no hourly charge. Trial 20 hours (6 months).
Pricing source, checked 2026-11-18
02 Languages 25
- Arabicar-SA
- Bengalibn-BD
- Cantoneseyue-CN
- Chinesezh-CN
- Dutchnl-NL
- Englishen-US
- Filipinofil-PH
- Frenchfr-FR
- Germande-DE
- Greekel-GR
- Indonesianid-ID
- Italianit-IT
- Japaneseja-JP
- Koreanko-KR
- Malayms-MY
- Nepaline-NP
- Polishpl-PL
- Portuguesept-BR
- Romanianro-RO
- Russianru-RU
- Spanishes-MX
- Thaith-TH
- Turkishtr-TR
- Ukrainianuk-UA
- Vietnamesevi-VN
03 Features 5 of 11 listed
- Word timestamps
- Speaker diarization
- Punctuationnot listed
- Profanity filter
- 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/volcengine/models/volc.seedasr.sauc.duration
Free, no key needed. Use model id volc.seedasr.sauc.duration with Volcengine's own API. API reference.