Back to Models
AlibabaOpen Source

Qwen3-ASR

Qwen3-ASR is a speech large model developed by Alibaba. It has a parameter scale of 8.0 billion and a context length of 128K, and is released under the Apache 2.0 license.

Parameters

8.0B

Context Window

128K

License

Apache 2.0

Release Date

2026-01-29

API Pricing

API pricing for this model is not yet available

Strengths

  • Long 128K context length
  • Sufficient 8.0B parameter scale
  • Open Apache 2.0 license

Weaknesses

  • Large model size (~16GB)
  • Voice-specific, limited versatility
  • Insufficient detailed performance metrics

Use Cases

  • Transcribing long audio data
  • Building large-scale speech recognition systems
  • Open-source-based audio analysis