Fact · Voice and AI
5seconds
In February 2025, Home Assistant said that Whisper on a Raspberry Pi 4 takes at least 5 seconds to turn speech into text, which is why it recommended at least an Intel N100 for fully local voice.
Checked against its source on October 17, 2026
In the source's own words
“takes at least 5 seconds to turn your speech into text”
Speech-to-Phrase brings voice home (Voice chapter 9), Home Assistant project, Home Assistant blog, 2025, Speech-to-Phrase introduction.
Open the original- What it measures
- This is an older figure than the eight seconds in the current documentation. The two differ because the test setups and model choices differ, and the project has not reconciled them in the sources checked.
- What it does not show
- The post's figure is a lower bound from February 2025. The current documentation's figure is about 8 seconds. Treat either as one project's measurement.