ASR 2
ASR 2 is Fireworks AI's speech to text model with a 4K context window and up to 4K output tokens. Fireworks AI's second-generation automatic speech recognition model for accurate audio transcription.
| Specifications | |
|---|---|
fireworks-ai-asr-2 | |
| Speech to Text | |
| Active | |
| Fireworks AI | |
| 4K tokens | |
| 4K tokens | |
| Audio | |
| Text | |
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·
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| ASR 2 | — | 4K | — | — | Current |
| ASR Large | — | 4K | — | — | Available |