fun-asr-realtime
This is the real-time version of Tongyi Lab's next-generation end-to-end speech recognition model, based on leading proprietary speech technology, and boasts exceptional contextual awareness and high-precision speech transcription capabilities. Based on an end-to-end architecture, Fun-ASR integrates innovative RAG technology, supporting multi-dimensional features such as large-scale hotword customization, automatic filtering of sensitive and modal particles, ITN normalization, and punctuation prediction, significantly improving overall recognition accuracy and contextual relevance. Furthermore, Fun-ASR supports flexible switching between Chinese and English, covers multiple regional dialects, and boasts enhanced noise robustness, adapting to diverse and complex environments.
Inference Service Provider
The inference service provider for fun-asr-realtime is Alibaba Cloud Model Studio.
Model Capabilities
| Capability | Support | Capability | Support |
|---|---|---|---|
Input Modality | Audio | Output Modality | Text |
Model Experience | Unsupported | Function Calling | Unsupported |
Structured Outputs | Unsupported | Web Search | Unsupported |
Prefix Completion | Unsupported | Context Caching | Unsupported |
Batch Inference | Unsupported | Fine-tuning | Unsupported |
Context Limits
| Parameter | Value | Parameter | Value |
|---|---|---|---|
Max Input Length | — | Max Output Length | — |
Context Window | — |
Pricing
This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit Model Studio Console for promotional offers.
China (Beijing)
| Billing Item | Price (CNY) | Unit |
|---|---|---|
Audio Duration | 0.00033 | Per second |
How to call the model
Rate Limits
China (Beijing)
| Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 1200 |
Singapore
Scope: International
| Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 1200 |
Snapshot Versions
fun-asr-realtime-2026-02-28
A new-generation lightweight real-time speech recognition model launched by Tongyi Bailing, built on a proprietary advanced speech technology architecture with powerful contextual understanding capabilities. It is designed for Chinese telephone customer service scenarios: covering dialects and accents from multiple regions, it delivers low-latency, high-accuracy streaming transcription in low-sampling-rate, low-SNR environments, meeting the needs of efficient deployment. This version is the snapshot released on February 28, 2026, with optimizations for near-field VAD.
Inference Service Provider
The inference service provider for fun-asr-realtime-2026-02-28 is Alibaba Cloud Model Studio.
Model Capabilities
| Capability | Support | Capability | Support |
|---|---|---|---|
Input Modality | Audio | Output Modality | Text |
Model Experience | Unsupported | Function Calling | Unsupported |
Structured Outputs | Unsupported | Web Search | Unsupported |
Prefix Completion | Unsupported | Context Caching | Unsupported |
Batch Inference | Unsupported | Fine-tuning | Unsupported |
Context Limits
| Parameter | Value | Parameter | Value |
|---|---|---|---|
Max Input Length | — | Max Output Length | — |
Context Window | — |
Pricing
This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit Model Studio Console for promotional offers.
China (Beijing)
| Billing Item | Price (CNY) | Unit |
|---|---|---|
Audio Duration | 0.00033 | Per second |
Rate Limits
China (Beijing)
| Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 1200 |