Your voice. On your device.

In the film

Say it

A human voice says: ‘I would like to see the figures for the second quarter.’ Dictivo’s Local transcription appears as a draft.

Your voice. On your device.

Local is the default. Once a model is installed, dictation audio is processed on your computer without uploading it.

Cloud, when you choose

A new draft opens, then Cloud Fast is selected. A second human recording says: ‘Everyone deserves to share in this success.’ Cloud Fast sends the selected recording for cloud transcription.

Keep your flow

Try Dictivo on Mac or Windows. All local models are free to try for 14 days, without a card or Dictivo account.

Spoken transcript

1. 0:02 Say it.
2. 0:04 I would like to see the figures for the second quarter.
3. 0:09 Make it happen.
4. 0:13 Your voice. On your device.
5. 0:21 Everyone deserves to share in this success.
6. 0:32 Keep your flow.

About this demonstration

The two dictation examples use original human recordings. Their displayed text comes from actual Local and Cloud Fast transcription. The film presents those results in a designed interface with shortened waits. Scene titles illustrate use cases; this is a product film, not a continuous screen recording or an accuracy comparison.

Local processes dictation audio on your computer after a model is installed. Cloud Fast uploads the recording you choose for cloud transcription. See how each mode handles audio.

Human recordings: CSTR VCTK v0.92, Yamagishi, Veaux and MacDonald (2019), University of Edinburgh. © 2019 Junichi Yamagishi. Recording collection · CC BY 4.0. Decoded to WAV, gain adjusted, gently compressed and mixed with music. No change to the words, voice speed or pitch. No endorsement. Music and brand narration are AI-generated.

Full film credits · Actual app captures and test conditions

Download the film

1080p film · 3.7 MB · 4K film · 10.2 MB · English captions · Chinese subtitles

When sharing the film, include the recording attribution and license in the accompanying description.