The Concat video editor makes subtitles from the speech in your project using Whisper, which runs on your own computer. Nothing uploads, there is no minute limit, and the result is a row of caption clips you can edit like any other text.
What do you need before you start?
You need Concat installed and one Whisper model. Open Settings, choose Transcriber and download a model. The list in Concat 0.2.7 has Tiny (78 MB), Base (148 MB) and Small (488 MB), each in English and multilingual versions. We used Base (English).
How do you add subtitles in the Concat video editor?
- Import your video and drag it onto the timeline. Make sure the clip with speech, or a voiceover, is on the timeline.
- Click the T captions button on the timeline toolbar.
- Switch on Use voice from timeline.
- Under Transcriber, pick the audio clip and the model.
- Choose a Placement (Bottom, Centre or Top) and a Size (Small, Medium or Large).
- Click Generate captions.
In our test, a 7-second English voiceover was transcribed in about 20 seconds on a CPU without a graphics card. The captions appeared as a pink title clip on the top lane, timed to the words.
How do you change the subtitle style?
Click a caption clip and the right panel shows its text settings: font, weight, size, italic, color, opacity, drop shadow and background. The Text tab also has preset styles such as Bold caption, Poster and Lower third. Click a caption in the preview to move or resize it.
Can you type the subtitles instead?
Yes. Leave Use voice from timeline off and type your words into Script. The Concat video editor splits the text into phrases and holds each one long enough to read. This is handy for silent clips, music videos or when you already have a transcript.
What did the result look like?
The transcript was accurate on a clear voice. Whisper capitalized “Vlog” in the middle of a sentence, so expect to fix a word or two by clicking the caption and editing the text.
Tips for better auto subtitles
- Use the multilingual model for anything that is not English.
- Clean noisy audio first with Reduce noise in the clip's Audio panel.
- Pick Large for vertical videos, since most people watch them on phones with the sound off.
- If the captions miss quiet words, try the Small model.
Want vertical captions for TikTok? Follow our TikTok video guide.
Watch it in Concat
We recorded this on Concat 0.2.7. Waiting time is sped up; every step is real.
- Type a script and generate a voiceover
- Generate captions from that voice
- Click a caption to edit and restyle it
