Capabilities
Explore what Fun-ASR Flash (2026-06-15) supports, then use the API section for a request tailored to this model.
Languages
Model Information
- Provider
- Alibaba Cloud Model Studio
- Product
- Speech-to-Text
- Release Date
- Jun 17, 2026
- Data Policy
- Not specified
- Region
- Global
- Input
- Audio
- Output
- Text
Playground
Try Fun-ASR Flash (2026-06-15) by Alibaba Cloud Model Studio. Requests use the selected workspace’s credits and API pricing.
Providers
Compare available endpoints, pricing, and context limits for Fun-ASR Flash (2026-06-15).
| Provider | Context | Output | Input Price | Output Price | Endpoint |
|---|---|---|---|---|---|
| Alibaba Cloud Model Studio | Not specified | Text | $0.0018 / minute | — | alibaba/fun-asr-flash-2026-06-15:alibaba |
Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.
Input and Output Limits
Formats and limits AudioLab enforces on each request.
| Limit | Value |
|---|---|
| Max bytes | 10000000 |
| Max seconds | 60 |
| Formats | aac, wav, mp3, mpeg, mpga, m4a, ogg, flac, opus |
Provider Notes
Dedicated Qwen ASR accepts byte uploads up to five minutes; Qwen3 Omni accepts inline audio up to 150 seconds. Fun-ASR Flash is the byte-input family with timestamp support. Qwen and Fun-ASR realtime use distinct native WebSocket event protocols. Reviewed file-transcription models accept uploaded audio through AudioLab's private expiring storage and recoverable provider jobs. Their final native duration receipt determines the charge.
Performance
Status
Current catalog availability. Your workspace’s access is checked separately before a request runs.
A live availability check is not available right now.
Getting Started
Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.
curl "$AUDIOLAB_API_URL/v1/audio/transcriptions" \
-H "Authorization: Bearer $AUDIOLAB_API_KEY" \
-F 'model=alibaba/fun-asr-flash-2026-06-15' \
-F 'file=@recording.wav'Request Parameters
Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.
| Parameter | Details |
|---|---|
model | alibaba/fun-asr-flash-2026-06-15 — Required model identifier. |
enable_itn / system_prompt (Qwen ASR batch) | View Accepted Values |
context / sample_rate (Fun-ASR batch) | View Accepted Values |
top_p / seed (Omni batch) | View Accepted Values |
mode / threshold / silence_duration_ms (Qwen realtime) | View Accepted Values |
corpus (Qwen realtime) | View Accepted Values |
vocabulary_id (Fun-ASR realtime) | View Accepted Values |
semantic_punctuation_enabled / max_sentence_silence (Fun-ASR realtime) | View Accepted Values |
multi_threshold_mode_enabled / speech_noise_threshold (Fun-ASR realtime) | View Accepted Values |
heartbeat | View Accepted Values |
Input and Output Limits
Formats and limits AudioLab enforces on each request.
| Limit | Value |
|---|---|
| Max bytes | 10000000 |
| Max seconds | 60 |
| Formats | aac, wav, mp3, mpeg, mpga, m4a, ogg, flac, opus |
Similar Models
Explore more speech-to-text and compare their capabilities.
| Model | Context | Input Price | Output Price |
|---|---|---|---|
| qwen-audio-3.0-asr-flashAlibaba Cloud Model Studio | Not specified | $0.0018 / minute | — |
| qwen-audio-3.0-asr-flash-filetransAlibaba Cloud Model Studio | Not specified | $0.0018 / minute | — |
| qwen-audio-3.0-asr-flash-streamingAlibaba Cloud Model Studio | Not specified | $0.0046 / minute | — |
| Qwen3.5 Omni FlashAlibaba Cloud Model Studio | Not specified | $0.0013 / minute | — |
| Qwen3.5 Omni PlusAlibaba Cloud Model Studio | Not specified | $0.0031 / minute | — |
| Qwen3-Omni FlashAlibaba Cloud Model Studio | Not specified | $0.0031 / minute | — |