Auto .ass + Speakers

Automatic .ass with
speaker tags built in.

Pxlify writes the speaker into the ASS Name field on every Dialogue line, so Aegisub, mpv, and modern players can colour and filter by speaker out of the box.

  • Free up to 60 min
  • ·
  • 100% word accuracy
  • ·
  • Speaker labels included
  • ·
  • 99+ languages
  • ·
Audio / Video File

Drag & Drop

MP3, MP4, M4A, MOV, AAC, WAV, OGG, OPUS, MPEG, WMA, WMV

— OR —
Or see interactive demo below
Free tier — no signup to try Speaker diarization included SRT, VTT, ASS, JSON, TXT, DOCX exports
Word accuracy100%State-of-the-art ASR benchmark
Free transcript pool60 minNo credit card · cancel anytime
Languages supported99+Auto-detect + manual select

Auto ASS Pipeline

Watch the exact pipeline that runs when you upload media to Pxlify.

pxlify_ai_engine_processor
Active Simulation
1

Upload & Extract

explainer_video.mp4

2

Whisper Speech AI

Converting audio to words...

3

Studio Transcripts

Synced SRT & VTT Exports

explainer_video.mp4

0%

Extracting high fidelity audio streams...

ASS subtitle generation with speaker tags

V4+ styles. Speakers in the Name field. Centi-second timing per spec.

Timed Highlights

Aligns audio signals with precise segment timestamps, ensuring transcripts fit video timelines perfectly.

Whisper Speech Model

Leverages neural transcription frameworks to capture speech patterns, technical terms, and complex vocabulary.

Multi-Format Exports

Export to SRT, WebVTT, Advanced SSA (.ass), JSON, Word (.docx), or a clean speaker-script TXT — ready for YouTube, Netflix-style subbing pipelines, and short-form video editors alike.

Interactive Playback

Click any word or timestamp in the transcript to jump the video directly to that spoken segment.

Privacy Secured

Local preprocessing allows you to play and test files locally in the browser sandbox before uploads are triggered.

Inline Studio Editor

Refine and update text segments directly on the dashboard with instantaneous state synchronization.

Generate a tagged .ass file in 3 steps

Upload, review speakers, export ASS.

01

Upload your video

Drag in a local file (.mp4, .webm, .mov) or pick an existing recording from your library.

02

Auto-generate timestamps

Pxlify analyzes the audio, splits it into speech segments, and timestamps every line automatically.

03

Refine & export

Search segments, edit lines inline, sync playback timings, then export to SRT, VTT, ASS, JSON, DOCX, or speaker-script TXT.

Auto ASS + speaker FAQs

Where do speaker tags appear in the ASS file?+

In the Name field of every Dialogue line — the canonical ASS convention.

Are V4+ styles included?+

Yes — sensible defaults (Arial 52, white fill, dark outline) ready for Aegisub.

Will the file open cleanly in Aegisub?+

Yes, with no warnings or format complaints.

Can I rename speakers before exporting?+

Yes. Rename in the Studio and the new names appear in the ASS Name field on export.