Add Subtitles in Final Cut Pro (2026): Native + AI-SRT Workflow

A Mac-based video editor friend pinged me last week: she'd just cut a 12-minute product walkthrough in Final Cut Pro and wanted to add Mandarin captions for an Asian market launch. Final Cut Pro 12.2's built-in Transcribe to Captions is impressive — for English. For Mandarin, Cantonese, Japanese, or mixed-language audio it's not yet supported (Apple's caption-creation guide explicitly limits the feature to spoken English-language audio as of May 2026). Her question: "What's the standard workflow now?"

This post walks Final Cut Pro's native subtitle features, where they work and where they fall short, and the AI-generated SRT workflow that fills the gap for non-English content.

Disclosure: I run Subanana, an AI subtitle and transcription tool. This guide cites Apple's published Final Cut Pro documentation and Subanana's product capabilities, pulled May 2026. No fabricated head-to-head benchmarks; both Final Cut Pro and Subanana have free tiers/trials, so test on your own footage if you want claim-level accuracy comparisons.

Method 1 — Final Cut Pro's native caption workflow

Final Cut Pro 12.2 ships a competent caption editor plus on-device Transcribe to Captions (Apple silicon, macOS Sequoia or later). For spoken English-language audio you can auto-generate captions from the timeline. For other languages, you still need an external transcription tool — Apple's caption-creation guide limits Transcribe to Captions to English audio as of May 2026.

Open your project in Final Cut Pro.
Add a caption track: Edit → Captions → Add Caption (or shortcut: Option+C). A new caption shows up over the playhead position.
Type the caption text into the caption inspector. Set the timing using the start/end controls.
Choose caption format: Inspector → Caption panel → select ITT (iTunes Timed Text), CEA-608, or SRT. ITT is the Apple-native format; SRT is universal.
Style the captions: Format → Captions → Caption Style to set font, color, position, background opacity.
Export with burned-in captions: File → Share → Master File → check Burn in Captions in the export options. Or export the SRT separately as a sidecar file.

Where this workflow shines: complete control over typography, color, position, and timing. The caption editor is well-integrated into Final Cut Pro's clip-level editing.

Where it falls short: Transcribe to Captions is English-only as of May 2026 (per Apple's user guide). For Cantonese, Mandarin, Japanese, Korean, or mixed-language audio you're still typing captions by hand — or importing them from an external tool.

Method 2 — Generate SRT with an AI tool, import into Final Cut Pro

The professional workflow for non-English or long-form content: outsource the transcription to an AI tool, then import the SRT into Final Cut Pro for styling.

Subanana was built for this gap. Multi-model evaluation across 80+ languages with best-per-language routing. Relevant for Final Cut Pro users:

80+ language coverage with per-language model selection — all major European languages, Mandarin, Japanese, Korean, Vietnamese, Thai, Cantonese, and many more.
Glossary support across all languages — pre-load brand names, product SKUs, and technical vocabulary so the recognition layer treats them as expected vocabulary. The single biggest review-time saver for branded content.
AI auto-correct pass cleans raw transcript output before you review it.
Speaker labels and editable transcripts before SRT export.
Direct SRT and VTT export in formats Final Cut Pro reads.

Workflow:

Open Subanana (plus.subanana.com). Upload your video file directly (MP4, MOV, M4V supported), or paste a YouTube / Vimeo URL if the source is online.
Select source language (or Auto-detect for mixed-language content).
Generate transcript. A 10-minute video typically completes in 2-3 minutes.
Edit transcript inline: fix names, technical terms, brand-specific vocabulary in Subanana's editor before export.
Optionally translate the transcript into target languages within Subanana — you'll get multiple SRT files, one per language.
Export as SRT.
In Final Cut Pro: File → Import → Captions → select the SRT file. Final Cut Pro reads the timecodes and aligns automatically.
Style the captions in Format → Captions → Caption Style. The content came from Subanana; the look-and-feel stays under your Final Cut Pro control.
Export with burned-in captions or as a sidecar SRT for platforms that support separate caption tracks.

Limitations to know

Final Cut Pro's native caption tools:

Built-in Transcribe to Captions is English-only (FCP 12.2, Apple silicon, macOS Sequoia+). For non-English audio you type captions manually or import from elsewhere.
Caption format options (ITT vs CEA-608 vs SRT) matter for downstream — Apple devices prefer ITT, web/social prefers SRT.

Subanana for Final Cut Pro workflow:

Subanana exports SRT and VTT — these are the formats Final Cut Pro imports cleanly. If you need a different caption format for downstream distribution, export SRT from Subanana then use Final Cut Pro's native re-export to convert.
Caption styling stays in Final Cut Pro. Subanana's role is generating accurate text + timecodes; the typographic look-and-feel is Final Cut Pro's strength and remains under your control.

FAQ

Can Final Cut Pro auto-generate captions from audio?

Yes for English — Final Cut Pro 12.2's Transcribe to Captions (Apple silicon, macOS Sequoia+) handles spoken English-language audio on-device. For other languages including Mandarin, Cantonese, Japanese, Korean, and mixed-language audio, Apple's documentation does not list support as of May 2026 — you need an external tool.

Which caption format should I use in Final Cut Pro?

SRT for YouTube, Vimeo, and most social platforms. Universal compatibility.
ITT for Apple TV+, iTunes, and other Apple ecosystem distribution.
CEA-608 for broadcast distribution.

Final Cut Pro can export to all three. Generate SRT from Subanana, import into Final Cut Pro, then re-export to the format your distribution needs.

Does the AI-SRT workflow add much time?

For a 10-minute video, the round-trip adds ~5 minutes (upload + processing + import). For non-English content where alternative would be typing captions manually, this is a 10x speedup.

How accurate is the AI on non-English audio?

Accuracy varies by language, audio quality, and content domain. The honest answer: better than typing from scratch, not perfect. Always review the transcript in Subanana's editor before export — fixing 5 terms is faster than typing 200 captions.

When to use which method

Short English video, scripted content → type captions manually in Final Cut Pro. Fast and gives complete control.
Long-form English video, podcast-style → AI-SRT workflow. Generate, edit lightly, import.
Non-English or mixed-language video → AI-SRT workflow. Final Cut Pro has no equivalent built-in option.
Multi-language distribution (one source, multiple language tracks) → AI-SRT workflow in Subanana, translate to target languages, import multiple SRT tracks to Final Cut Pro.

How to Add Subtitles in Final Cut Pro (2026): The Full Workflow + AI-SRT Workaround for Non-English Content