Audio · Speech-to-text · Released Sep 2022
OpenAI Whisper Base
A small on-device Whisper model that transcribes speech in the app with no API key, trading accuracy for speed.
Whisper Base is an open-weight speech-to-text model built by OpenAI. It transcribes spoken audio into written text. It runs entirely on your own hardware through Hugging Face: no API key and no per-use fees.
Supported OS
macOSWindowsLinux
Minimum machine configuration
4 GB RAM · CPU · multilingual
Download size · ~0.15 GB
Specs
- Released
- 4 years ago (Sep 2022)
- Pricing
- Free, runs on your hardware
- Type
- Speech-to-text
About the creator
OpenAI
OpenAI builds GPT, DALL·E, the Sora family, and the open-weight gpt-oss models, and has been a central force behind the modern wave of generative AI.
openai.com ↗More from OpenAI
GPT 6 Astra
TextCloud
OpenAI's flagship GPT-6 model for complex reasoning, coding, research, and long-running agent work, with vision and a 1M-token context window.
GPT 6 Sol
TextCloud
OpenAI's cost-efficient high-end GPT-6 tier for demanding coding and agentic work, with vision and a 1M-token context window.
GPT 6 Sol Pro
TextCloud
GPT 6 Sol in OpenAI's pro reasoning mode, which works longer on each answer for higher quality on hard tasks.
GPT 6 Luna
TextCloud
OpenAI's fast, low-cost GPT-6 tier for high-volume chat, classification, and light agentic work, with vision.
GPT 6 Luna Pro
TextCloud
GPT 6 Luna in OpenAI's pro reasoning mode, which works longer on each answer for higher quality on hard tasks.
GPT 5.4
TextCloud
OpenAI's frontier model with advanced reasoning and broad multimodal capabilities.