# Qwen3-ASR Flash

`qwen3-asr-flash` — **qwen** · TRANSCRIPTION

> Qwen3-ASR Flash (qwen3-asr-flash) is a transcription model from qwen with a 53.2K-token context window; proprietary (API-only); input audio; output text.

| Field | Value |
| --- | --- |
| Vendor | qwen |
| Kind | TRANSCRIPTION |
| Context window | 53,248 tokens |
| Max output tokens | 4,096 tokens |
| Input modalities | audio |
| Output modalities | text |
| Weights | Proprietary (API-only) |
| Knowledge cutoff | 2024-04 |
| Release date | 2025-09-08 |
| Sources | models-dev |
| Last verified | 2026-10-30 |

*Part of the [Model Catalog](https://openviglet.github.io/model-catalog/) — [qwen models](https://openviglet.github.io/model-catalog/models/qwen/) · [Vendor JSON](https://openviglet.github.io/model-catalog/by-vendor/qwen.json) · [HTML](https://openviglet.github.io/model-catalog/models/qwen/qwen3-asr-flash.html)*