OpenAI · Transcription
whisper
Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multitasking model that can perform multilingual speech recognition, speech translation, and language identification.
- Official partner's price
- $0.006 /min
- Listings
- 4
- Providers
- 4
Evidence and sources
Model architecture, as its sources state it
Maker HQ: US (according to OpenAI's own website)
Sources: Cloudflare Workers AI, LiteLLM dataPrimary data from Cloudflare Workers AI
from LiteLLM: deprecation date
Advantages and trade-offs
Compared with 10 representative transcription models
Advantages
Trade-offs
Deprecation scheduled
The maker plans to deprecate it on 15 Dec 2026, within the next 180 days.
Costs more than most peers
Official partner's price: $0.006 /min, pricier than 5 of 5 priced peers.
Input & output
as stated by the model's providersText
Audio
Text
Also known as: azure/whisper, azure_ai/whisper, cloudflare/@cf/openai/whisper, deepgram/whisper, openai/whisper
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