OpenAI Whisper Small
A mid-sized on-device Whisper model that transcribes speech in the app with no API key, balancing speed and accuracy.
Whisper Small is an open-weight speech-to-text model built by OpenAI. It transcribes spoken audio into written text. It handles multiple spoken languages and can return timestamped segments along with the transcript. It runs entirely on your own hardware through Hugging Face: no API key and no per-use fees.
- Released
- Sep 2022
- Pricing
- Free, runs on your hardware
- Type
- Speech-to-text
- Languages
- Multilingual
- Timestamps
- Timed segments
Samples
Transcribed by Whisper Small via Hugging Face. The same three clips go to every speech-to-text model in the catalog, so the only thing that changes between two models’ transcripts is the model. The clips are synthetic speech made with ElevenLabs v4, and a word that differs from the spoken script is underlined. The numbers clip is left unmarked, since “12” and “twelve” are both right.
Baseline accuracy and punctuation on clean speech
Thanks for joining on such short notice. We moved the launch to Thursday, so could you send me your notes before lunch? I will share the final schedule with everyone tomorrow morning.
Thanks for joining on such short notice. We moved the launch to Thursday, so could you send me your notes before lunch? I will share the final schedule with everyone tomorrow morning.
How dates, amounts, units and a surname are written out
Invoice 4471 is due on March 3rd, 2027. The total comes to $1,249.50 for 12 units, and the parcel weighs 2.5 kilograms. Please call Dr. Elena Markovic at 9:45 a.m. to confirm.
Invoice 4471 is due on March 3rd, 2027. The total comes to $1,249.50 for 12 units, and the parcel weighs 2.5 kg. Please call Dr Elena Markovich at 9.45am to confirm.
Background noise, a second accent, speaker changes
Excuse me, is this seat taken? No, go ahead. Are you heading to the conference as well? I am. Do you know which stop it is? The one after the river, I think. We can walk over together.
Excuse me, is this seat taken? No, go ahead. Are you heading to the conference as well? I am. Do you know which stop it is? The one after the river, I think. We can walk over together.
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 ↗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 Astra in OpenAI's pro reasoning mode, which works longer on each answer for the highest quality on hard tasks.
OpenAI's life sciences model, with specialized biological reasoning and scientific tool use. Only organizations approved through OpenAI's trusted-access program can call it, for internal research.
OpenAI's cybersecurity model for investigating vulnerabilities, reproducing them in an authorized test environment and verifying fixes. Only organizations approved through OpenAI's Daybreak program can call it.
OpenAI's update to GPT 6 Sol, the cost-efficient high-end GPT-6 tier, for agentic coding and document work, with vision and a 1M-token context window.
OpenAI's fast, efficient GPT-6.1 tier for visual reasoning, computer use and clear writing, improving on GPT 5.6 Terra with a 1M-token context window.