Fact · Speech recognition
31.34percent word error rate
In our October 2026 test on a Mac with an M2 Pro, Apple SpeechTranscriber had a word error rate of 31.34 percent on 100 English FLEURS recordings with background talk 5 dB quieter than the speaker (a loud cafe).
Measured by us on October 19, 2026, from 100 recordings
Our own measurement
This number comes from our benchmark, not from another publication. The full record (the setup, every recording's checksum, every transcript and timing) is published, so you can recompute it.
- What it measures
- Apple's on-device speech model in macOS 26 (SpeechAnalyzer with a SpeechTranscriber module, transcription preset), with the locale given (en-US, de-DE, fr-FR, es-MX, it-IT, pt-BR). The same 100 English recordings as our main benchmark, so the conditions differ only in the noise added.
- How it is measured
- Word error rate = 671 word errors / 2,141 reference words = 31.34 percent. Babble = four other speakers from the same recordings at equal loudness, mixed at 5 dB below the speaker.
- What it does not show
- Babble made from read sentences is steadier than a real cafe (no dishes, music or sudden laughter), and a close microphone in a real room changes the ratio. Compare engines and conditions, not this number with a real room.
In the data
A row of Dictation in Noise: Speech Recognition Accuracy Tested, as Apple SpeechTranscriber, 5 dB: 31.34 percent.
- Engine
- Apple SpeechTranscriber
- Maker
- Apple
- Background talk
- 5 dB
- Language
- English