Skip to main content
Language models take your transcribed text and format or transform it according to your mode’s instructions. There are two types: cloud models run on hosted servers, and local models run entirely on your device. Usage of every model below is covered by your license, with no API keys needed.
Speed is a relative rating from 1 to 10. Our benchmarks cover voice models only; see How We Benchmark for what we measure.

​
Superwhisper (Cloud)

Hosted by Superwhisper and optimized for low latency and high-quality text processing.

​
Superwhisper (Local)

S1-mini runs entirely on your device, on macOS and Windows (Windows ARM devices need a cloud model instead). It cleans up English punctuation, numbers, dates, and fillers. It works offline, and with a local voice model nothing you dictate leaves your machine. S1-mini is English only. It works only in Message and Mail modes, so it can’t run Super, Note, Meeting, or Custom modes.

​
Anthropic (Cloud)

Anthropic’s Claude models, available through Superwhisper.

​
OpenAI (Cloud)

OpenAI’s GPT models, available through Superwhisper.

​
Google (Cloud)

Google’s Gemini models, available through Superwhisper.

​
Groq (Cloud)

Inference hosted on Groq’s LPU hardware. Superwhisper updates its list of cloud language models from the server, so new models can appear in the app before this page changes.

​
Legacy models

The app marks these older models as deprecated: GPT-4.1, GPT-4.1 mini, GPT-4.1 nano, GPT-4o, GPT-4o mini, GPT-3.5 Turbo, GPT-5.3 Instant, Sonnet 4, Sonnet 3.7, Sonnet 3.5, Sonnet 3, Haiku 3.5, Gemini 3.1 Flash Lite, and Grok 4.1 Fast. Use a current model from the tables above instead.

​
Choosing a model

S1-Language is the default and the right choice for most modes. Pick S1-mini when you dictate English in a Message or Mail mode and want the whole pipeline on-device. Reach for a larger model (GPT-5.2, Sonnet 5, Gemini 3.7 Flash) only when a mode does heavy rewriting and quality matters more than speed. You can also add models from your own providers with your own API keys under Settings → Models library → Bring your own keys.