Private and open-source alternatives to Dragon
5 accessibility rated against the same public privacy criteria as Dragon (Dragon NaturallySpeaking), with our picks first.
Why look for an alternative?
- Open source: no. Closed source.
- No trackers or telemetry: no. The cookie statement says third-party analytics and advertising network cookies are used on Nuance websites.
- No ads or data sales: no. Sold as paid software, but the cookie statement says third-party advertising networks use cookies to target Nuance ads to visitors on other sites.
- Independent audit: no. No independent audit is published.
The alternatives
eSpeak NG Grade B
Open source speech synthesizer supporting more than 100 languages and accents, used as a text-to-speech engine by screen readers such as NVDA and Orca.
eSpeak NG scores 80 out of 100 (grade B) on the accessibility criteria. It meets 3 of 4 criteria: open source, no trackers or telemetry and no ads or data sales.
NVDA Grade B
Free, open source screen reader for Windows that reads screen content aloud by speech or braille display. Developed by the Australian non-profit NV Access.
Based in Australia (Five Eyes). NVDA scores 80 out of 100 (grade B) on the accessibility criteria. It meets 3 of 4 criteria: open source, no trackers or telemetry and no ads or data sales.
Orca Grade B
Free, open source screen reader for Linux desktops that gives access to applications through speech and braille, using the AT-SPI accessibility framework. Part of the GNOME project.
Orca scores 80 out of 100 (grade B) on the accessibility criteria. It meets 3 of 4 criteria: open source, no trackers or telemetry and no ads or data sales.
Speech Note Grade B
Open source Linux app for taking, reading and translating notes with offline speech-to-text, text-to-speech and machine translation. Processing runs locally on the computer.
Speech Note scores 80 out of 100 (grade B) on the accessibility criteria. It meets 3 of 4 criteria: open source, no trackers or telemetry and no ads or data sales.
Vocalinux Grade D
Offline voice dictation for Linux on X11 and Wayland that types speech into the focused app. Speech recognition runs locally with engines such as whisper.cpp and VOSK.
Vocalinux scores 50 out of 100 (grade D) on the accessibility criteria. It meets 2 of 4 criteria: open source and no ads or data sales.