Streaming speech-to-text model for low-latency transcript deltas from live audio
- Released
- 5mo ago
- Pricing
- Not published
Sources:models.dev
Benchmarks
DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.
Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.
No benchmark results have been matched to this model yet.
Specifications
Additional source evidence
- Source model
- openai/gpt-realtime-whisper
- Source family
- whisper
- Last updated
- 2026-05-07
- Model context
- 16K
- Model output limit
- 2K
- Open weights
- No
- File attachments
- No
- Reasoning
- No
- Tool calling
- No
- Temperature control
- Yes
Complete source record (JSON)
{
"id": "openai/gpt-realtime-whisper",
"name": "GPT Realtime Whisper",
"description": "Streaming speech-to-text model for low-latency transcript deltas from live audio",
"family": "whisper",
"last_updated": "2026-05-07",
"attachment": false,
"reasoning": false,
"tool_call": false,
"temperature": true,
"modalities": {
"input": [
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 16000,
"output": 2000
},
"release_date": "2026-05-07",
"open_weights": false
}Infrastructure
Provider availability
Provider-specific media pricing is not available in the imported source data yet.
Text provenance
EU · product-scopedOpenAI textGrain watermarking
In the EU, ChatGPT-generated text uses textGrain. OpenAI says API customers can opt in globally for select models, so watermarking depends on the product surface and configuration.
Official explanation