Identifying Speakers/People
Understand how FilmScribe automatically identifies different speakers in your audio. Diarization separates who says what, making it easier to organize and edit your content.
Explore other features
Supported Content
21 content types with exclusive emotional vocabulary. AI adapts to your project's context.
Narrative Hooks
Moments with the highest narrative potential, identified by AI with impact scoring and narrative function.
Smart Chapters
Your audio automatically divided into thematic chapters with mood, topics, and exportable timestamps.
Project Organization
Folders with colors, tags, and descriptions. All your clients and projects in one place.
Clear Narrative Timeline
Transcription, emotions, and hooks in a unified timeline with visual navigation.
Download Audio by Emotion/Lines
Bookmark clips, export as MP3, WAV, TXT, or SRT. Cut audio ready to use.
Supported Languages
100+ languages with automatic detection and per-word timestamps.
Supported Formats
MP3, WAV, M4A, AAC, OGG, OPUS, WEBM. Upload as is, no conversion needed.
Video & YouTube
Upload videos or paste YouTube links. Audio is extracted automatically. Download the full video in the available quality.
Subtitle & Content Translation
Translate subtitles and full content into 9 languages. Export translated SRT or FCPXML.
Auto & Manual Clips
Ready-to-post clips derived from hooks and emotions, with an inline editor to trim time and remove words before exporting MP4.
Burned-in & Animated Captions
Various classic and animated templates, 23 fonts, keyword highlighting, and a preview identical to the final video.
Vertical Reframing + Auto-Pan
Convert to 9:16, 1:1, or 4:5 with the camera automatically following whoever is speaking. Hard cuts between speakers.
Image & Text Overlays
Add your logo, images, and text over your clips, drag, resize, and set the time window right in the preview.
