OpenAI · Transcription
OpenAI Whisper 1
Whisper-1 speech-to-text transcription trained on multilingual supervised audio, with a 25 MB upload limit per file.
- Maker's price
- $0.006 /min
- Max context
- 448K
- Listings
- 13
- Providers
- 13
Evidence and sources
Maker HQ: US (according to OpenAI's own website)
All rankings:
#666 on OpenRouter today
#698 on OpenRouter this week
#760 on OpenRouter this monthSources: OpenAI API data, EmpirioLabs data, Core42 Compass Model Pricing, Models.dev dataPrimary data from OpenAI API
from EmpirioLabs: name, primary mode, deprecation date, description
from Core42 Compass Model Pricing: variant
from Models.dev: weights availability
Advantages and trade-offs
Compared with 10 representative transcription models
Advantages
Trade-offs
Deprecation scheduled
The maker plans to deprecate it on 25 Feb 2027, within the next 180 days.
Costs more than most peers
Maker's price: $0.006 /min, pricier than 5 of 5 priced peers.
No open weights
The weights aren't public, so you can't run it yourself.
Input & output
as stated by the model's providersText
Audio
Video
Text
Also known as: azure/whisper-1, openai-whisper-1, openai/whisper-1
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works