Fact · Dictation in your apps
10GB of video memory
The large Whisper model needs about 10 GB of video memory according to OpenAI's model table.
Checked against its source on October 17, 2026
In the source's own words
“large 1550 M N/A large ~10 GB 1x”
openai/whisper: Robust Speech Recognition via Large-Scale Weak Supervision, OpenAI, GitHub (OpenAI repository), 2023, Available models and languages table.
Open the original- What it measures
- The model table in the openai/whisper README, read on 2026-10-17.
- What it does not show
- The figure is OpenAI's estimate of required video memory for each model size, not a measurement on a laptop.
Source
Cited on
- How to Transcribe Audio to TextGuide
- What Is Whisper AI? OpenAI's Speech Model ExplainedGuide
- Speech-to-Text APIs Compared: Price, Accuracy, SpeedGuide
- Video to Text: Transcribe Videos and YouTubeGuide
- Transcription Software: How to Choose OneGuide
- How to Run Whisper Locally on Your Own ComputerGuide
- Web Speech API: Speech Recognition in the BrowserGuide
- Can Whisper run in the browser?Question
- Can you transcribe audio offline without uploading it?Question
- How can I transcribe audio to text for free?Question
- Is ElevenLabs speech to text better than Whisper?Question
- Is there a free speech-to-text API?Question
- What is the best GPU for Whisper?Question
- Which Whisper model should I use?Question
- Why is Whisper not using my GPU?Question