ASR Realtime
ASR Realtime is Alibaba's language model. A real-time automatic speech recognition model designed for streaming audio transcription with low latency.
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard |
|---|---|
| Audio In $ / sec | |
| $0.000090 | |
| $0.000047 |
Cost Calculator
US Dollar ($)
Preset:
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Text 4 Embedding | — | — | $0.070 | — | Available |
| Text 3 Embedding | — | — | $0.070 | — | Available |
| HappyHorse 1.0 | — | — | — | — | Available |
| ASR Realtime | — | — | — | — | Current |
| ASR | — | — | — | — | Available |
| ASR Flash | — | — | — | — | Available |
| ASR Flash 8K Realtime | — | — | — | — | Available |
| ASR MTL | — | — | — | — | Available |
| ASR MTL Realtime | — | — | — | — | Available |
| Coder | — | 1.0M | $0.300 | $1.50 | Available |
| Coder Plus | — | 131K | $0.502 | $1.00 | Available |