West Central speech: voice note to text tools compared for Oromo; the code-switching dissertation was built on recordings of spontaneous informal conversation.
This page compares voice note to text tools for Oromo. Oromo is spoken in Ethiopia, Kenya and Somalia.
A 2026 dissertation (Wakwoya Tolosa, University of Pannonia) analysed 21 hours of spontaneous informal conversation by 56 bilingual speakers and found Afaan Oromoo is the matrix language with English contributing embedded words that fit Oromo grammar, plus minor Amharic contact.
| Option | What its page shows about Oromo | Source |
|---|---|---|
| Autrans | Autrans offers Oromo. Measured result: Word error rate 79.7% on read speech, FLEURS test set, measured Sep 2026. | autrans.online |
| Sonix | The list on the Sonix page does not include Oromo. | sonix.ai |
| Descript | The list on the Descript page does not include Oromo. | help.descript.com |
| Trint | The list on the Trint page does not include Oromo. | info.trint.com |
| Maestra | The list on the Maestra page does not include Oromo. | maestra.ai |
| VEED | The list on the VEED page does not include Oromo. It says: "Twi, Sesotho and Oromo are translation-only, so recorded as no for transcription." | support.veed.io |
| TurboScribe | The pages read for TurboScribe say nothing about Oromo. | turboscribe.ai |
| Rev | The pages read for Rev say nothing about Oromo. | rev.com |
| Happy Scribe | The pages read for Happy Scribe say nothing about Oromo. It says: "Yoruba, Hausa, Igbo, Shona, Somali, Xhosa, Wolof, Lingala, Twi, Oromo, Setswana and Nigerian Pidgin are not in the table." | happyscribe.com |
Named: its page names the language. Not listed: its own list leaves the language out. Not stated: the pages read say nothing either way, so test a file. All pages read on 22 October 2026.
Word error rate 79.7% (95% confidence interval 74.9–84.4%) on read speech, FLEURS test set, measured Sep 2026. Only 41 recordings were available, far fewer than a stable estimate needs, so treat the figure as a rough indication. Measured on 41 recordings. Word error rate is the share of words that differ from a human-written transcript, so lower is better. Read speech means people reading set sentences aloud, so conversation, background noise and phone-quality audio will usually score worse. Test set: FLEURS (Google).
Upload the voice note file, choose the language it is in, and Autrans returns a transcript you can read, search and edit.
Languages here: Oromo.
Yes, Oromo is one of the live languages. Word error rate 79.7% (95% confidence interval 74.9–84.4%) on read speech, FLEURS test set, measured Sep 2026.
Sonix, Descript, Trint and Maestra did not list Oromo on the pages we read on 22 October 2026. A page that does not list a language may still handle it, so test a file.
Send Autrans into your next meeting, use it in the room, or upload a recording. Your first 30 minutes are free, given once, and no credit card is needed to start.
Last checked 22 October 2026. How we measure accuracy. Spotted a mistake? Write to hello@autrans.online.