Captions & Transcription

Generate a transcript from your recorded speech in CANVID, then use it for captions, navigation, and transcript-based editing.

CANVID can generate a transcript from the spoken audio in your project, making it easier to review what was said, show captions in your video, and work faster in the editor.

You can use the generated transcript to:

Show or hide captions in the preview
Click words to jump to that moment in the recording
Copy the transcript as plain text or SRT
Continue into transcript-based tools like AI Retakes

Generate a Transcript

If you want to understand current Local AI hardware support, see Local AI Requirements.

Go to the editor

Finish a new recording, or open an existing project file that includes a voice recording.

Captions sidebar

Click the Text icon to open the Captions sidebar.

Setup your Transcript

Click the Generate Transcript button to get started.

Transcription Settings

Choose your transcript settings:

Mode
- Local: Processes the transcript on your machine, but may require extra downloads.
- Cloud: Generates the transcript online, which requires no downloads and is generally faster.

Local mode is only available on Windows. Transcript generation on Mac uses Cloud instead.

Language: Choose the language that matches the language used in your voice recording.

Choosing a different language will not automatically translate your voice recording.

Quality (Local Mode only): If you notice transcription accuracy issues on Normal, switch to High for better results, though processing may take slightly longer.
Prompt: Use this to improve transcription accuracy, especially for unique names, terms, or specialized vocabulary.

Start Generating

Click Generate Transcript to start processing.

Show Or Hide Captions

Use the Show Captions toggle to turn visible captions on or off in the preview.

Customize

Collapsing this section will show additional options:

Word Highlighting: Visually highlights words in sync with the voice recording, making it easier to follow speech in your video.
Caption Size: Choose from Small, Medium, or Large presets, or use the slider below for more precise size control.

Save a copy of your transcript: In the Transcript section of the Captions sidebar, clicking the Copy icon allows you to copy your generated transcript to the clipboard in TXT or SRT format.

Transcript Editor

Timeline Navigation via Transcript

Click words in the transcript to jump to that point in your video.

Correction Tools

Double click a word or highlight a phrase in the transcript to show special editing tools:

Correct Text: use this option to fix typos, spelling, or to replace entire words or phrases.

Replace Audio: Correct speech mistakes by re-recording or typing new audio, with changes automatically synced to your webcam.

Learn more: AI Retakes

Cut: Removes a section of the transcript from your video. This opens a new window where you can fine tune your audio selection to ensure accurate results.

Re-Generate The Transcript

If you want to try different settings, click Re-Generate Transcript.

If you have already corrected transcript text in the editor, re-generating the transcript resets those transcript edits.

AI Webcam

Add your webcam after recording with CANVID's Synthetic Webcam. AI lip-syncs your face to match audio, so you always look polished, even if you didn’t record live.

AI Retakes

Fix mistakes in your screen recordings with CANVID's Audio Retakes. Re-record or type new audio and sync your webcam with AI for a polished, professional result.