GPT-Realtime-Whisper
OpenAI
- Released
- -
- Data date
- September 22, 2026
- Model class
- Access
GPT-Realtime-Whisper is a dedicated streaming model for real-time transcription. It turns audio streams into text and lets developers tune latency and accuracy. Its documented output path is transcript deltas rather than spoken replies. Unlike GPT-Realtime 2.1, OpenAI documents text output and audio input for the realtime transcription workflow.
The documented context window is 16,000 tokens, with a 2,000-token maximum output. Function calling and structured outputs are not supported. OpenAI lists a September 30, 2024 knowledge cutoff. Its narrow specialization is reflected in the audio-input, text-output contract. OpenAI bills it by audio duration rather than text tokens.
Specifications and access
| Specification | Value and source |
|---|---|
| Model class | Streaming speech recognitionSource |
| Access | APISource |
| API model ID | gpt-realtime-whisperSource |
| Input | Audio streamSource |
| Output | TextSource |
| Task | Streaming transcriptionSource |
| Supported details | For real-time audioSource |
| Context window | 16,000 tokensSource |
| Maximum output | 2,000 tokensSource |
| Knowledge cutoff | 2024-09-30Source |
Measurements without matching peer values
These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.
Artificial Analysis AA-WER Streaming (final transcription) (Show measurement, test conditions, and source)
- Source value
- 4.8854
- Score
- 4.8854
- Metric
- word error rate (WER)
- Unit
- %
- Benchmark version
- AA-WER v2.2 streaming
- Category
- audio
- Direction
- Lower is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-10-15
- Methodology
- Independent evaluation. Direct API streaming evaluation; final-transcription WER across AA-AgentTalk (50%), VoxPopuli (25%), and Earnings22 (25%), about eight hours total. WER is duration-weighted within dataset; Earnings22 chunking is reassembled at parent-call level. AA-WER v2.2 streaming protocol.
Popularity
34.2 / 100
Published prices
- Live transcription price
- $0.017 per audio minuteSource
Sources and data date
| Type | Evidence and data date |
|---|---|
| Research status | Research date October 15, 2026. 4 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication. |
| Additional source | OpenAI model documentation (retrieved September 22, 2026; October 15, 2026) · OpenAI GPT-Realtime-Whisper model documentation · Editorial description reviewed October 2, 2026 |
| Additional source | Artificial Analysis (retrieved October 15, 2026) |
| Additional source | Model metadata (retrieved October 15, 2026) |
| Additional source | OpenRouter: Popularity index (derived), CC BY 4.0 |
| Additional source | Vercel AI Gateway: Popularity index (derived), CC BY 4.0 |
| Additional source | Creative Commons Attribution 4.0 |