Model Tracker
whisper-1
whisper-1 is an AI model made by OpenAI. It takes audio and returns text. Its licence is MIT License.
In inglese
- Released
- Not confirmed: The maker's API announcement says Whisper is available through the API, but the cited page does not print the original announcement date; its visible date is an update date, not a stated first-availability date.
- Status
- Not confirmed: two readings disagree: deprecated and ga
- Takes
- Audio — developers.openai.com, read 19 October 2026
- Returns
- Text — developers.openai.com, read 19 October 2026
- Open weights
- Not confirmed: two readings disagree: true and false
- Licence
- MIT License — github.com, read 19 October 2026
- Context window
- Not confirmed: The maker's cited model and API pages do not print a standard context-window value for whisper-1.
- Longest answer
- Not confirmed: The maker's cited model and API pages do not print a standard maximum-output token limit for whisper-1.
- Knowledge cutoff
- Not confirmed: The maker's cited pages do not print a knowledge-cutoff date for whisper-1.
- API price, input
- Not confirmed: The maker publishes transcription pricing per minute, not a standard input price per 1 million tokens. The page does not give an input/output price split, and converting the unit is not permitted by the register rules.
- API price, output
- Not confirmed: The maker publishes transcription pricing per minute, not a standard output price per 1 million tokens. The page does not give an input/output price split, and converting the unit is not permitted by the register rules.
- Where
- Not confirmed: two readings disagree: api, weights and api
- Parameters
- Not confirmed: The maker's model card lists parameter counts for Whisper model sizes but does not print a parameter count specifically for whisper-1 or Whisper V2 large-v2.
- Model card
- https://github.com/openai/whisper/blob/main/model-card.md — github.com, read 19 October 2026
Questions
What is the licence of whisper-1?
The licence of whisper-1 is MIT License, as OpenAI names it.
What does whisper-1 take and return?
whisper-1 takes audio and returns text.
More from OpenAI
- ada
- babbage
- babbage-002
- code-davinci-002
- computer-use-preview
- curie
- dall-e-3
- DALL·E
- DALL·E 2
- davinci
- davinci-002
- GPT-3.5 Turbo
- GPT-3.5 Turbo Instruct
- GPT-4
- GPT-4 Turbo
- GPT-4.1
- GPT-4.1 mini
- GPT-4.1 nano
- GPT-4.5
- GPT-4.5 Preview
- GPT-4o
- GPT-4o mini
- GPT-4o Mini Search Preview
- GPT-4o Mini Transcribe
Sources
- Whisper Model | OpenAI API (read 19 October 2026)
- Deprecations | OpenAI API (read 19 October 2026)
- Create transcription | OpenAI API Reference (read 19 October 2026)
- Introducing ChatGPT and Whisper APIs | OpenAI (read 19 October 2026)
- GitHub - openai/whisper: Robust Speech Recognition via Large-Scale Weak Supervision (read 19 October 2026)
- whisper/model-card.md at main · openai/whisper (read 19 October 2026)