Whisper
Whisper is OpenAI's speech to text model, available from 3 providers. A general-purpose automatic speech recognition model trained on diverse multilingual audio, supporting transcription and translation tasks.
openai-whisper |
| Speech to Text |
| Active |
| OpenAI |
| 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·
Pricing by Provider
| Provider | Standard | |
|---|---|---|
| Audio In $ / 1M | Audio Out $ / 1M | |
 Deepgram | $0.000100 | N/A |
 Azure AI Foundry | $0.000100 | $0.000100 |
OpenAI | $0.000100 | $0.000100 |
Cost Calculator
Preset:
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Whisper 3 | — | 4K | — | — | Available |
| Whisper 3 Large | — | — | — | — | Available |
| Whisper 3 Large Turbo | — | — | — | — | Available |
| Whisper 3 Turbo | — | 4K | — | — | Available |
| Whisper 2 Large | — | — | — | — | Available |
| Whisper | — | — | — | — | Current |
| Whisper Base | — | — | — | — | Available |
| Whisper Large | — | — | — | — | Available |
| Whisper Medium | — | — | — | — | Available |
| Whisper Small | — | — | — | — | Available |
| Whisper Tiny | — | — | — | — | Available |