qwen
Qwen: Qwen3 ASR 0.6B
qwen/qwen3-asr-0.6b
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
qwen/qwen3-asr-0.6b is an audio-to-transcription model in OpenRouter’s catalog and the 0.6B member of Qwen’s Qwen3-ASR family. Qwen describes language identification and speech recognition across 30 languages plus 22 Chinese dialects, with one model supporting offline and streaming operation and inputs ranging from speech to singing or songs with background music. Vendor documentation positions this variant as the efficiency-oriented option, but the supplied pack contains no independent accuracy or latency evaluation.[1][2]
Strengths
- OpenRouter lists an audio-only input and transcription output for this exact variant.[1]
- Qwen documents language identification and transcription for 30 languages and 22 Chinese dialects.[2]
- A single model is documented for offline and streaming inference over speech, singing voice, and songs with background music; Qwen reports an efficiency-oriented throughput profile.[2]
Limitations
- Evidence is limited to catalog metadata and Qwen documentation; no independent benchmark or third-party evaluation for this exact variant was supplied.[1][2]
- Streaming is documented only through the vLLM backend and does not support batch inference or timestamps.[2]
- Timestamps require the separate Qwen3-ForcedAligner-0.6B, and the pack does not state a maximum audio duration or measured accuracy for qwen/qwen3-asr-0.6b.[1][2]
Where to use it
- Consider for multilingual transcription services where automatic language identification and broad Chinese-dialect coverage matter.[2]
- May suit high-volume offline transcription workloads if vendor efficiency claims hold under the target hardware and audio.[2]
- Potentially useful for streaming captions or voice-note processing through vLLM when batching and timestamp output are unnecessary.[2]
Sources
- [1] OpenRouter catalog · Qwen: Qwen3 ASR 0.6BSources checked: Nov 13, 2026
- [2] Model documentation · Qwen: Qwen3 ASR 0.6BSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Qwen3 ASR 0.6B is a compact automatic speech recognition model from Qwen. It supports multilingual language identification and transcription across 30 languages and 22 Chinese dialects, with streaming and offline...
Specifications
- Model ID
- qwen/qwen3-asr-0.6b
- Canonical ID
- qwen/qwen3-asr-0.6b-20260813
- Creator
- qwen
- Added to OpenRouter
- 13.08.2026
- Context length
- 0
- Modality
- audio->transcription
- Input modalities
- audio
- Output modalities
- transcription
- Token pricing
- No per-token price in the source snapshot — see OpenRouter for the billing unit
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | — |
| Coding | No measurement | — |
| Agents | No measurement | — |
| Writing | No measurement | — |
| Reasoning | No measurement | — |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | input: audio |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| PrimeIntellectbf16 | 0 | — | — | — | — | 100% |
| DeepInfra | 0 | — | — | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.