Overview
Qwen-Audio-3.0-ASR-Flash-Streaming is a real-time, streaming automatic speech recognition model designed for low-latency, high-concurrency interaction. It accepts audio and returns text. Alibaba lists its release date as July 30, 2026. (alibabacloud.com)
Capabilities and uses
- Streams transcription as speech is received, with context enhancement and support for precompiled and on-the-fly hotwords.
- The release announcement describes support for 30 languages, including Chinese, English, Japanese and Korean; seven major Chinese dialect groups; and more than 20 regional accents. It also describes improved classical Chinese poetry recognition, punctuation prediction and normalization of numbers, dates and monetary amounts.
- Intended uses include live meeting transcription, customer-service assistance, voice assistants, education and subtitles. (alibabacloud.com)
Integration and limits
- Real-time input must be mono. The documented binary-stream formats are PCM, WAV, MP3, Opus, Speex, AAC and AMR; the guide lists any sample rate and no audio size or duration limit for this model.
- The model information page lists function calling, structured outputs, web search, prefix completion, context caching, batch inference and fine-tuning as unsupported. It does not specify maximum input, output or context lengths. (alibabacloud.com)
Official API pricing
Checked November 16, 2026. Prices below apply to this exact 3.0 Streaming model. Input is billed by audio duration in seconds; text output is free. Domestic and international account prices are separate offerings, not currency conversions. The current pricing tables list no free quota for this model. (help.aliyun.com)
| Official pricing site and deployment region | Input price | Output price |
|---|---|---|
| Mainland China site, China North 2 (Beijing) | CNY 0.00033 per audio second | Free |
| Mainland China site, Singapore, international deployment | CNY 0.00066 per audio second | Free |
| International site, Singapore, international deployment | USD 0.00009 per audio second | Free |
| International site, China (Beijing) | USD 0.000047 per audio second | Free |
Official pricing sources, checked November 16, 2026: Mainland China pricing and international pricing. (help.aliyun.com)