Every File You Get After AI Dubbing: Perso AI Download Guide

Perso AI delivers 10 downloadable files from a single dubbing project — not just the dubbed video. You get the dubbed MP4, source and translated audio tracks (WAV), separated speaker audio (TAR), isolated background music (WAV), source and translated subtitles (SRT), and bilingual scripts (XLSX). Every file is available from the Starter plan at $6.99/month. This guide explains what each file is, when to use it, and how to download it.

By the numbers: Every AI dubbing platform exports the dubbed video. A few also export subtitles and audio tracks. Perso AI exports 10 file types from every dubbing project — including isolated background music, bilingual XLSX scripts, and speaker-separated audio — all available from the Starter plan at $6.99/month. No Enterprise gate. No add-on fees.

What Files Does Perso AI Export After Dubbing?

Here is the complete list of files you can download after any Perso AI dubbing project:

Perso AI generates all 10 files automatically. No add-ons, no extra credits, no separate tools. One dubbing project, 10 outputs.

See Every File You Get with One Dub

1. Dubbed Video Export (MP4)

What it is: The final dubbed video — your original footage with the translated voiceover replacing the source audio. Voice cloning preserves the original speaker’s tone, pacing, and cadence. Lip-sync is applied automatically.

When to use it:

• Publishing the dubbed version directly to YouTube, TikTok, or your LMS

• Embedding on landing pages or product pages for different markets

• Sharing with stakeholders for review before distribution

What makes it different: Perso AI’s MP4 export includes lip-sync by default. Most competitors require a separate step or charge extra for lip-sync processing.

2. Source Audio Export (WAV)

What it is: The original audio track from your uploaded video, extracted as a high-quality WAV file.

When to use it:

• Archiving the clean original audio before dubbing

• Using the original voiceover in a different editing project (Premiere Pro, DaVinci Resolve, Final Cut)

• Comparing original vs. dubbed audio quality side by side

3. Source Audio by Speaker (TAR)

What it is: A compressed archive containing individual audio files for each speaker detected in the original video. If your video has 3 speakers, you get 3 separate WAV files.

When to use it:

• Podcast editors who need to adjust volume or EQ per speaker independently

• Interview videos where one speaker needs re-recording while others stay

• Multi-speaker QA — checking that each speaker’s voice was correctly cloned

Why this matters: Speaker-separated audio typically requires dedicated tools like Descript or Adobe Podcast. Perso AI includes it automatically in every dubbing project. For a deeper dive, see How to Export Speaker-Separated Audio from Video.

4. Translated Audio Export (WAV)

What it is: The dubbed voiceover audio only — no video, no background music. Just the translated voice track.

When to use it:

• Podcast localization: publish an audio-only version in another language

• Replacing audio in your own editing timeline (Premiere, Final Cut) for custom post-production

• Voiceover-only distribution for radio, internal training audio, or audiobook-style content

Pro tip: If you’re re-editing in your own NLE, download the Translated Audio (no BGM) and the BGM Export separately. This gives you full control over the mix ratio between voice and music. See How to Download Dubbed Audio Without Video for the full workflow.

5. Translated Audio with BGM (WAV)

What it is: The dubbed voiceover mixed with the original background music — ready to use as a complete audio track without the video.

When to use it:

• Audio-first distribution (podcasts, internal comms, audio newsletters) where you want the full “produced” sound

• Quick turnaround: no manual mixing needed, the BGM balance is already set

• Social media audio clips with background music preserved

6. BGM Export (WAV)

What it is: The isolated background music from your original video — all vocals removed. Clean instrumental track only.

When to use it:

• Re-mixing dubbed audio at a custom voice-to-music ratio in your DAW or editor

• Using the original BGM in promotional clips, trailers, or highlight reels

• Checking whether the AI correctly separated music from speech (QA step)

Why this is rare: No other AI dubbing platform exports BGM separately. Perso AI’s audio separation engine isolates vocals and background music during processing, and makes both available as individual downloads. See How to Extract Background Music from Video with AI for the full guide.

7. Source Subtitles (SRT)

What it is: Auto-generated subtitles in the original language of your video, exported as a standard SRT file. Perso AI’s speech recognition covers 100 languages for transcription.

When to use it:

• Adding closed captions to the original video on YouTube or Vimeo

• Accessibility compliance (ADA, WCAG) for your existing content

• Feeding the SRT into other translation tools or workflows

• SEO: uploading SRT to YouTube improves discoverability in the original language

Format details: Standard SRT with sequence numbers, timestamps (HH:MM:SS,mmm), and subtitle text. Compatible with YouTube, Vimeo, Premiere Pro, Final Cut, DaVinci Resolve, and every major video platform. For the complete SRT workflow, see How to Auto-Generate SRT Subtitles from Any Video.

8. Translated Subtitles (SRT)

What it is: Subtitles in the target language, time-synced to match the dubbed audio timing — not the original speech timing.

When to use it:

• Dual-language publishing: upload both Source Subtitles and Translated Subtitles to YouTube as multiple caption tracks

• Accessibility in the target market

• Burned-in subtitle workflows where you hardcode subtitles into the video using FFmpeg or your editor

Key difference from competitors: Many subtitle translation tools generate translated text but don’t adjust timing to match dubbed audio pacing. Perso AI’s translated SRT is synced to the actual dubbed voiceover, so subtitles appear at the right moment — not when the original speaker was talking.

9. Source Script (XLSX)

What it is: The full transcription of your original video exported as a spreadsheet. Each row corresponds to a segment, with columns for timestamp, speaker label, and transcribed text.

When to use it:

• Content repurposing: turn a video script into blog posts, social captions, or email copy

• Legal/compliance review of what was actually said in the original recording

• Searchable archive: XLSX is easily searchable, sortable, and filterable

10. Source & Translated Script (XLSX)

What it is: A bilingual spreadsheet with the original text and translated text side by side. Each row shows the same segment in both languages, with timestamps and speaker labels.

When to use it:

• Translation QA: Reviewers can scan both versions line by line without switching between files

• Language learning content: Educators use bilingual scripts as study materials

• Localization team handoff: Project managers share the XLSX with local reviewers who don’t have access to Perso AI

• Compliance documentation: Regulated industries (medical, legal, financial) keep bilingual records of what was said and how it was translated

Why XLSX and not PDF? Spreadsheets are editable, sortable, and filterable. If a reviewer flags a translation issue in row 47, the editor can jump directly to that timestamp in the Perso AI editor and fix the line. See Bilingual Script Export: Side-by-Side Translation for QA & Learning for use cases and workflows.

How to Download Your Files: 3 Steps

Step 1. Complete your dubbing project in Perso AI (Upload > Select language > Process).

Step 2. On the project results page, click the Download button. A dropdown menu shows all available file types.

Step 3. Select the file you need. Each file downloads individually, so you can pick exactly what you need without downloading a bulk archive.

All 10 file types are available from the Starter plan ($6.99/month) onward. The Free plan does not include file exports.

Which Files Do Competitors Export?

Where Perso AI Stands Out

ElevenLabs comes closest with 8-9 export types, including speaker-separated WAV tracks and CSV bilingual scripts. But three differences remain:

1. BGM Export is Perso AI only. No other platform on this list lets you download the isolated background music as a separate WAV file. For creators who need to remix dubbed audio at a custom voice-to-music ratio, this is the only option that doesn’t require a separate stem-separation tool.

2. Every file from $6.99/month. ElevenLabs gates some exports behind higher tiers. HeyGen requires Pro+ for SRT and script downloads. Synthesia restricts script export (XLIFF) to Enterprise. Perso AI makes all 10 files available from the Starter plan.

3. XLSX over CSV. ElevenLabs exports bilingual scripts as CSV — useful for developers, less intuitive for marketing teams, translators, and project managers. Perso AI exports as XLSX with structured columns, ready to open in Excel or Google Sheets without conversion.

Frequently Asked Questions

Q. Are all 10 download files included in the Starter plan, or do some require a higher tier?

All 10 file types are available from the Starter plan ($6.99/month). There is no per-file charge or add-on fee. The only feature restricted by plan tier is SRT Upload (custom subtitle import before dubbing), which is available on the Enterprise plan only. By comparison, HeyGen restricts SRT and script exports to Pro+, and Synthesia limits script export to Enterprise.

Q. Can I download files from a project I completed weeks ago?

Yes. All completed projects and their downloadable files remain accessible in your Perso AI dashboard. You can return to any past project and download any of the 10 file types at any time.

Q. What audio quality are the WAV exports?

Perso AI exports WAV files at the source quality level. WAV is an uncompressed lossless format, so there is no quality loss from compression. This makes the exports suitable for professional post-production workflows in DAWs and video editors.

Start Exporting More Than Just a Video

One dubbing project. Ten files. Video, audio, subtitles, scripts — everything you need to repurpose your content across every format your audience uses.

Try Perso AI free No credit card required. 10 export types from Starter. 33+ dubbing languages.

Internal Links:

• What Is AI Dubbing? The Complete 2026 Guide

• How to Translate a Video: 3 Methods Compared

• Best AI Dubbing Tools 2026: 9 Platforms Tested & Ranked