GPT-Realtime-Whisper
OpenAI
- Context window
- 16K 16,000 tokens
- Max output
- 2K 2,000 tokens
- Input / Output
- audio, text → text
Timeline
- · API availability · evidence link
Evidence links
gpt-realtime-whisper· standard · openai · Estimated cost: ≈ $0.017 / minute
- · Catalogue listing · GitHub · openai/openai-python · code
Excerpt
}, "session": { "model": "gpt-realtime-translate", "audio": { "input": { "transcription": { "model": "gpt-realtime-whisper" }, "noise_reduction": null }, "output": { "language": "es" } } } }' response: | { "value": "ek_68af296e8e408191a1120ab6383263c2", "expires_at": 1756310470, "session": { "id": "sess_C9CiUVUzUzYIssh3ELY1d", "type": "translation", "expires_at": 1756310470, "model": "gpt-realtime-translate", "audio": {
This code reference does not establish a working model identifier.
Specifications
GPT-Realtime-Whisper is a model from OpenAI, released on 7 May 2026. The context window is 16,000 tokens. The maximum output is 2,000 tokens.
- Context window
- 16,000
- Max output
- 2,000
- Input
- audio · text
- Output
- text
Questions
What is the context window of GPT-Realtime-Whisper?
The context window is 16,000 tokens. The maximum output is 2,000 tokens.
When was GPT-Realtime-Whisper released?
On 7 May 2026.