# gpt-realtime-whisper

> gpt-realtime-whisper is a proprietary language model from OpenAI, released on 7 May 2026. It accepts audio and generates text.

Source page: https://www.aimodel.directory/models/gpt-realtime-whisper
Last verified: 4 Oct 2026

## Specifications

- **Developer:** OpenAI
- **Release date:** 7 May 2026 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/vercel/models/openai/gpt-realtime-whisper.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/vercel/models/openai/gpt-realtime-whisper.toml)
- **Weights:** Proprietary (API only) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/vercel/models/openai/gpt-realtime-whisper.toml)
- **Input:** Audio (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/vercel/models/openai/gpt-realtime-whisper.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/vercel/models/openai/gpt-realtime-whisper.toml)
- **Reasoning mode:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/vercel/models/openai/gpt-realtime-whisper.toml)
- **Tool calling:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/vercel/models/openai/gpt-realtime-whisper.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| Vercel AI Gateway | – | – | – | – |

## FAQ

### Is gpt-realtime-whisper open source?

No. gpt-realtime-whisper is a proprietary model; OpenAI has not released its weights. It is available through APIs including Vercel AI Gateway.

### When was gpt-realtime-whisper released?

OpenAI released gpt-realtime-whisper on 7 May 2026, according to models.dev.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "gpt-realtime-whisper", https://www.aimodel.directory/models/gpt-realtime-whisper