Qwen3 ASR 1.7B
Qwen3 ASR 1.7B is the larger open-weight speech recognition model from Qwen. Transcribes 30 languages and 22 Chinese dialects with automatic language detection. Language hints may be ignored. Accepts MP3, WAV, FLAC, and OGG recordings up to 10 minutes, with direct uploads up to 4 MB or audio URLs up to 25 MB. Returns a completed JSON transcript without timestamps, speaker labels, or translation. Billed per started input second.
Added Nov 18, 2026
Details
- Approx. Price
- <$0.001 per minute
- Model type
- speech-to-text
- Category
- speech-to-text
- Preview examples
- 0