vsref
Distil-Whisper logo

Distil-Whisper Review

OSS

Distilled Whisper: near-Whisper accuracy at a fraction of the size and up to 6x the speed, English-only, MIT-licensed

Among the 43 speech-to-text tools we track, Distil-Whisper has the 43rd-widest language coverage.

See pricing

Facts verified Jul 20, 2026Website →

What we know about Distil-Whisper

This is our verified profile of Distil-Whisper, a speech-to-text apis platform - distilled Whisper: near-Whisper accuracy at a fraction of the size and up to 6x the speed, English-only, MIT-licensed. Every fact about Distil-Whisper below carries the source it came from and the day we checked it.

Distil-Whisper does not publish a public per-minute rate we have been able to verify, so the price figure here stays blank until we can confirm one. We would rather show nothing than a guessed number; if you have a current Distil-Whisper quote, it is the fastest way for us to close that gap.

On capabilities, Distil-Whisper covers word-level timestamps and self-host / on-prem option, and does not offer language auto-detection and speech translation. Each of those is verified against Distil-Whisper's own docs or dashboard, not marketing copy.

Placed against the 43 speech-to-text tools we track, Distil-Whisper's strongest showing is the 43rd-widest language coverage - a spread worth weighing against your own priorities.

In total we track 14 verified facts for Distil-Whisper today, each linking the primary source it came from so you can check our work - and vendor claims we have not measured ourselves are labeled as such on the Distil-Whisper fact sheet below.

Reviewed by vsref Editorialfacts verified Jul 20, 2026Methodology →

Fact sheet

Capabilities
Capabilities facts
WER (vendor-claimed)~7.08 % WERJul 20
Languages supported1 languagesJul 20
Language auto-detection✗ NoJul 20
Speaker diarization✗ Not availableJul 20
PII redaction✗ Not availableJul 20
Word-level timestamps✓ YesJul 20
Speech translation✗ NoJul 20
Compliance & trust
Compliance & trust facts
Self-host / on-prem option✓ YesJul 20
Model weights licenseMITJul 20
Build experience
Build experience facts
Official SDKsTransformers, whisper.cpp, faster-whisper + moreJul 20
Commercial
Commercial facts
Model size (parameters)166M-756M across sizes; flagship 756MJul 20
Hardware to self-hostCPU-capable; GPU recommended (FA2/SDPA supported)Jul 20
Project maintenance statusHF models updated 2026-04; GitHub last commit 2025-01Jul 20
GitHub stars4,100 starsJul 20

Considering a switch? Best Distil-Whisper alternatives →

Voice agents in this stack

The engine is one layer: a voice agent hears through its transcription engine, but orchestration, telephony, and turn-taking come from the agent platform. Compare the platforms builders pair Distil-Whisper with: Pipecat, OpenAI Realtime API, Twilio ConversationRelay, or the full voice-agent comparison →

Want it done for you?

Distil-Whisper gets you a transcript; the bot that joins the call, labels speakers, and writes the summary is still your build. If that is more pipeline than you want to own, AI meeting notetakers do the whole job end to end: Otter.ai, Fireflies.ai, Fathom, or the full notetaker comparison.