Alibaba Cloud: Qwen3 ASR Flash Filetrans

Qwen3 ASR Flash Filetrans is the file-transcription member of the Qwen3 ASR family. Timestamp options make it useful for preparing searchable recordings and subtitles that need to remain aligned with the original audio.

Compare models

qwen3-asr-flash-filetrans

AvailableAlibaba CloudSpeech to TextSync / Async

Price: From $0.000035
Modalities: Audio

About Qwen3 ASR Flash Filetrans

Qwen3 ASR Flash Filetrans is the long-file member of Alibaba's Qwen3 ASR family, run as an asynchronous job. Alibaba's native service documents recordings up to 2 GB and 12 hours, while the upload endpoint linked here has a separate 25 MB limit. Where Qwen3 ASR Flash handles clips of about five minutes, this variant targets full meetings and lectures, with word timestamps in ten listed languages.

Where it works well

Alibaba's native service documents recordings up to 2 GB and 12 hours; uploads through the endpoint linked here are limited to 25 MB.
Word-level timestamps cover Chinese, English, Japanese, Korean, German, French, Spanish, Italian, Portuguese, and Russian.
Alibaba documents emotion recognition for this model; it is not a guaranteed field of the shared response.
Timestamps make output usable for subtitle files and searchable archives.

When to choose another model

Jobs complete after processing, so interactive voice input needs Qwen3 ASR Flash Realtime.
Alibaba highlights timestamps and emotion for this model, not speaker labels; Fun-ASR and Paraformer v2 list speaker separation.

Getting started

Create API key
Create a key in Console, then use it with every model on the platform.

Send your first request

Copy the example for your language and run it against the endpoint.

Speech to textTokenLab endpoint

POST/v1/audio/transcriptions

curl -X POST "https://api.tokenlab.sh/v1/audio/transcriptions" \
  -H "Authorization: Bearer sk-xxx" \
  -F file="@audio.mp3" \
  -F operation="stt" \
  -F response_format="json" \
  -F model="qwen3-asr-flash-filetrans" \
  -F language="en"

Parameters

Speech to text

Parameter	Values and limits	Default	Notes
`file`	Inputs: ≥ 1, ≤ 1	Not provided	Send one audio file in multipart/form-data. Maximum file size is 25 MiB.
`language`	Not provided	Not provided	This field is accepted. The current public contract does not specify a complete value range or list. No additional values are promised. The omitted-field default is not verified.
`response_format`	Not provided	`json`	Omit this field to use json. The current route creates an asynchronous transcription task and returns JSON task status and results. This field does not select an audio output encoding. Other response formats have not been qualified for this model.
`timestamp_granularities`	Not provided	Not provided	Not provided
`timestampGranularities`	Not provided	Not provided	Not provided

Pricing

The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.

Speech to text

per second

Official price: $0.000035
Verified price: —
Discount: —

	Official priceper second	Verified priceper second	Discount
Speech to text	$0.000035	—	—

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours

Requests
Success rate
P95 latency
Total tokens

Model performance

Last updated Nov 1, 2026, 8:13 AM UTC

Metrics appear once privacy and data volume thresholds are met.

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open Qwen3 ASR Flash Filetrans in Console with a prompt ready to edit or send.

Help me try qwen3-asr-flash-filetrans with a short audio request at /v1/audio/transcriptions. Show the result and cost.

Use cases

Subtitle generation
Create time-aligned subtitles for a video, using the word-level timestamps the model details list to cut lines at natural breaks.
Lecture search
Transcribe course recordings prepared within the upload limit so students can search for a topic and jump to its moment.
Multilingual archives
Process recordings in any of the ten timestamp-supported languages with one model, instead of keeping a separate tool per language.

Prompt examples

Transcribe this 20-minute conference recording within the 25 MB limit with the timestamp options in the model details.

Transcribe this Japanese training clip and show me the returned transcript fields.

Transcribe this lecture excerpt and return the timing information the model reports.

FAQ

How does Filetrans differ from Qwen3 ASR Flash?

Filetrans runs asynchronously; Alibaba's native service documents files up to 2 GB and 12 hours, and the upload endpoint linked here has a separate 25 MB limit. Qwen3 ASR Flash answers synchronously for clips of roughly five minutes. Pick by recording length.

Which languages get word timestamps?

Alibaba's native asynchronous API returns sentence timings by default and uses enable_words for word timings in Chinese, English, Japanese, Korean, German, French, Spanish, Italian, Portuguese, and Russian. For the endpoint linked here, request only the timestamp options advertised in the current model details and inspect the returned transcript fields.

Does it tag emotion?

Alibaba documents emotion recognition for this model natively. Native emotion annotations are not a guaranteed field of the shared response, so inspect the returned transcript before relying on a mood tag.

Can it identify speakers?

Alibaba's page for this model highlights timestamps and emotion, not diarization. If you need speaker labels in the transcript, Fun-ASR and Paraformer v2 list that feature explicitly.

How much does Qwen3 ASR Flash Filetrans cost?

On TokenLab, Qwen3 ASR Flash Filetrans costs $0.000035 per second. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

Which endpoint should Qwen3 ASR Flash Filetrans use?

Use https://api.tokenlab.sh/v1/audio/transcriptions for Qwen3 ASR Flash Filetrans. The request example below shows the matching code shape.

Which operations does Qwen3 ASR Flash Filetrans support?

Qwen3 ASR Flash Filetrans supports Speech to text. Select an operation above to see its endpoint and request example.