Help

Everything you need to know about using Paper Edit App.

Building your paper edit

How do I start a project?

Open the Paper Edit Bridge panel inside Premiere Pro and click "Send to Paper Edit". There are no files to export or upload — the Bridge reads your sequence and its transcripts directly, you build the paper edit by selecting words in the browser, and the Bridge builds the finished sequence back in Premiere.

How do I add something to my paper edit?

Drag across the words you want in the transcript, exactly like selecting text. On release, that exact word range becomes a block in the paper edit panel on the right — snapped to whole words. A selection can cross speaker boundaries; it stays one block. A plain click does nothing, so you can't create a block by accident. One constraint: a block must sit within a single clip — you can't drag from the tail of one clip into the start of the next (you'd see an error message if you tried). This is because each block's timecodes are relative to one clip's media time, and spanning two clips would misplace it when the Bridge builds the sequence.

How do I fine-tune a block's in/out points?

  • Click a block in the paper edit panel — its words highlight in the transcript and drag handles appear at the start and end.
  • Drag a handle word-by-word to trim or extend.
  • Click the block again (or elsewhere) to finish.

What do the Timecodes, Pauses and Tints toggles do?

They sit above the transcripts and apply everywhere at once — to every transcript column and the paper edit. Timecodes prefixes each paragraph with its start time. Pauses reveals silence and filler gaps flagged by Premiere (hidden by default). Tints turns the per-speaker background shading on or off (speaker labels always stay). They're view-only — they never change what's stored.

How does the Pauses toggle work, and what do I set in Premiere?

Premiere flags silence and filler gaps in the transcript but doesn’t export the actual words — so Paper Edit shows them as […] (short pauses) or [Xs] (pauses over 2 seconds), hidden by default for a cleaner read. Toggle Pauses on to reveal them.

To enable filler-word detection in Premiere:

  • Open Window → Text → Transcript
  • Click the ••• menu and choose Transcript view options…
  • Enable filler-word detection
  • Re-transcribe the sequence
  • Re-send from the Bridge panel

Tip: transcripts created outside Premiere, or older ones, usually have no filler-word flags.

How do labels, markers and notes work?

Each block has a row of icons. The tag icon adds a label — it becomes a blue marker in Premiere. The single speech-bubble icon is for markers: click a word inside the block to drop a precise orange marker at that word's exact source time, then type a note that becomes the marker's comment in Premiere. A Frame.io comment imported onto a word (see "Can I bring in comments from a Frame.io review?" below) shows the same way and becomes an identical marker on build. The pencil icon is Edit mode (remove words / split a block). The stacked speech-bubbles icon opens collaborator comments for that block (see "Working together" below) — it's separate from markers and never touches the Premiere timeline. The trash icon deletes the block. Colours match the Premiere timeline: labels are blue, markers are orange.

Can I rename or merge speakers?

Yes. Double-click a speaker chip above a transcript to rename it; right-click a chip to reassign everyone with that speaker to another. Renames and merges update the transcript, the tints, and any blocks already using that speaker. The original transcript is never altered — overrides are reversible.

Can I undo, redo, reorder and clear?

Cmd+Z (or the Undo button in the paper edit header) undoes any change — create, delete, reorder, label, note, boundary, or clear. Cmd+Shift+Z (or the Redo button) re-applies it. Drag the grip handle to reorder blocks. "Clear: Blocks | Labels | Notes" in the header clears each, and clearing is undoable too. If a save ever fails the change is rolled back and a message appears. In a shared project your undo only affects your own changes, never a collaborator's.

How do I set the output sequence settings for multiple sources?

The Settings button — in the top-right of the page header — controls what the built sequence is set to. With several sources that have different frame rates or resolutions, it warns you and lets you choose: match the first source, match the last, or set frame rate and resolution manually.

How do I export, and how does the build work?

The Export button (top-right of the page header) downloads a Paper Edit JSON of your edit, or prints it (Save as PDF). To build the actual sequence, go back to the Bridge panel in Premiere and click Build — it pulls your paper edit and reconstructs the trimmed clips in order, with linked video/audio and your markers. There's no XML or SRT in this workflow.

Working together — live editing, comments & suggestions

Can more than one person edit at the same time?

Yes. A shared paper edit is live. When you and a collaborator (a producer, director, or co-editor) have it open at once, every change — adding, trimming, reordering, labelling, or deleting a block — appears in each other's window within about a second. You each control your own transcript columns and layout, but you're all shaping the same paper edit. It also works asynchronously: if someone edits while you're away, you'll see their changes the next time you open the project.

How do I know who else is in the project?

When someone else has the same paper edit open, a green dot and an avatar showing their initials appears in the page header, between the project name and the Comments button. Hover it to see their email; it disappears when they leave. Up to three avatars stack side-by-side, with "+N" if more are present. There are no live cursors — it's a light "who's here" indicator.

If we both edit at the same time, will we clash?

Each block is handled independently, so two people working on different blocks never interfere. If you both change the very same block at the same moment, the most recent save wins. Your Undo only ever affects your own actions — undoing can't remove a change a collaborator made.

Can I undo and redo?

Yes. Cmd+Z (Ctrl+Z on Windows) undoes your last change; Cmd+Shift+Z (Ctrl+Shift+Z) redoes it. Both are also buttons in the paper edit header (Undo / Redo). Every kind of change is covered — create, delete, reorder, label, marker, trim, clear. In a shared project, undo affects only your own changes, never a collaborator's.

How do comments work?

Open Comments from the Comments button in the page header (next to Request review), or click the stacked-speech-bubbles icon on any block. Comments then sit in a margin to the right of the paper edit, each thread anchored beside the block it's attached to — like Google Docs — so as you scroll the paper edit the comments scroll with it. A composer bar sits at the top for writing new comments; comments that aren't tied to a specific block ("Whole paper edit") group there too. Post a comment and collaborators see it live and get a notification. You can reply to build a thread, Resolve a thread once it's handled (and Reopen it later), and delete your own comments — project owners can delete any. A block that has comments shows a small blue count badge on its comments icon.

What's the difference between a comment and a suggestion?

A comment is discussion. A suggestion is a proposed edit that can be applied with one click. There are four ways to make one: in the composer bar at the top of Comments, switch the title toggle from "Comments" to "Suggest" — then choose an op. With a block focused (click its comments icon or select it), you can propose removing it, relabelling it, or moving it to a different position in the paper edit. To propose adding a new block, pick "Add block", choose where it should go in the paper edit, then click "Select words in transcript" — this puts the transcript in selection mode so you can drag to select the words you want to propose adding. The fourth path is from a block's Edit mode: mark words to remove and click "Suggest" instead of applying directly (a trim suggestion). Suggestions are ideal for a reviewer who wants to propose changes without altering the edit directly.

How do I accept or reject a suggestion?

Open the Comments panel. Each open suggestion shows what it proposes — e.g. "Proposes removing this block" or "Proposes relabelling to …" — with Accept and Reject buttons. Accept applies the change immediately, exactly as if you'd made the edit yourself, so it syncs to everyone and can be undone with Cmd+Z. Reject leaves the paper edit untouched and marks the suggestion rejected. Anyone on the project can accept or reject, and the person who suggested it gets a notification either way. (If the target block has changed too much since the suggestion was made, Accept will tell you it can no longer be applied.)

What does "edited by …" on a block mean?

In a shared project, if a collaborator was the last person to change a block, a small "edited by [name]" note appears in that block's header. It only shows when someone other than you made the last change, so you can see at a glance what a collaborator has touched.

How do I tell collaborators the edit is ready to review?

Click Request review in the paper edit header. Everyone else on the project gets a notification that you'd like them to take a look. It's the lightweight handoff for asynchronous work — they can pick it up whenever they're next free. Producers and clients have the same button in their header.

What's the difference between Request review and Sign off?

Request review means "take a look and give me feedback" — it's the everyday, mid-process handoff, and either the editor or a producer can send it at any point. Sign off means "this is final — I'm done, go build it in Premiere." Only a producer or client can sign off (an editor never signs off their own work to themselves), and it's meant for the very end of a producer's pass, not a general-purpose nudge. Both just send a notification — signing off doesn't lock the paper edit or stop anyone editing it further.

Can I save and load different versions of my paper edit?

Yes. Click Versions in the paper edit header, then "Save version…" and give it a name (e.g. "Rough cut", "Producer's pass"). This snapshots the current paper edit — every block, label, and note — under that name. Anyone with access to the project (owner or a shared producer/client) can save, load, or delete a version. Loading a version replaces the live paper edit with that snapshot; it's destructive and can't be undone, so you'll be asked to confirm. If you've already saved or loaded a version this session, Save version offers to update that same version in place instead of always creating a new one — handy for iterating on "the same cut" without the list filling up with near-duplicates; choose "Save as new version" instead if you want to keep the old one too. The header shows which version the paper edit was last saved as or loaded from, and that version is marked "Current" in the Versions list — though further edits since then won't be reflected there until you save again.

Do comments and suggestions need an AI key?

No. Live editing, presence, comments, and suggestions all work without any AI key — they're part of the core collaboration features. AI keys are only needed for AI search, the Topics tab, and the Refine tab.

Search, AI search & the Refine tab

How does keyword search work?

Use the search bar at the top of each transcript column. Type a word or phrase, then jump between matches with the ↓/↑ arrow keys or Enter (next match), or the arrow buttons next to the search bar. Press Escape to clear. Matches highlight in yellow.

Which AI providers are supported, and what does it cost?

Claude (Anthropic), OpenAI, and Gemini (Google). You use your own API key and pay the provider directly — there is no markup. A typical search on a 500-block transcript costs less than half a US cent. Gemini via Google AI Studio has a free tier and is the easiest way to get started at no cost.

What do the AI search error messages mean?

"Your AI key appears to be invalid" — check the key you pasted in Settings, it may have been entered incorrectly or expired. "Your AI account has run out of credits" — top up your balance with your provider. "Rate limit reached" — you've hit your provider's per-minute request cap; wait a moment and try again. If AI search fails entirely, keyword search always works without a key.

What is the Refine tab?

The Refine tab is an AI editorial assistant that reads your existing paper edit and surfaces structured observations to help you think more clearly about your choices. It never makes changes automatically — every suggestion requires a deliberate action. Switch to the Refine tab (above the transcript columns) once you have a draft paper edit you want to review.

What kinds of suggestions does the Refine tab give?

Four types: Repetition — two or more spans that cover the same idea or near-identical phrasing. Pacing — a section taking up a disproportionate amount of runtime relative to its ideas. Trim candidate — spans that feel redundant relative to what surrounds them (only when you've set a time target). Arc — a high-level observation about narrative structure, such as resolving before it builds or opening with the conclusion. For multi-speaker edits, the AI includes speaker context in its analysis — observations may note which speaker a span comes from, and suggestions about balance or repetition can reference individual speakers by name.

How do I use the Refine tab?

Switch to the Refine tab, optionally enter a target duration (e.g. "1:30" or "90s"), then click "Analyse". The AI reads your current paper edit and returns a set of observation cards. Each card shows a neutral observation, a question to sit with, and a "Block N" button per relevant block that jumps you to it. Some cards include a "Remove block N" button — hover it to see why it's suggested, and it shows how much runtime removing it would save. You can dismiss any card with the ✕ button. If you keep editing after analysing, an amber banner appears ("Your paper edit changed since this analysis") with a one-click Re-analyse.

What does "Find alts" do?

Clicking "Find alts" on a Refine suggestion card switches you to the Sources tab and pre-fills the AI search with the text of the relevant span. The search fires automatically so you can browse alternatives from the full transcript pool — the rest of the rushes you haven't selected yet. On multi-source projects a "Find alts: This source / All" toggle appears above the suggestions so you can choose whether to search only the source the span came from or all sources at once. When you find something better, select it as normal and switch back to Refine to re-analyse.

What happens when I click "Remove block N"?

The block is deleted from your paper edit the normal way — which means Cmd+Z immediately recovers it. The suggestion card disappears once the removal succeeds. There is no "Apply all" button; each suggestion is acted on individually or dismissed.

Does the Refine tab require an AI key?

Yes — the same key you save for AI search is used for the Refine tab. Go to Settings → AI API Keys and paste a key for any supported provider (Claude, OpenAI, or Gemini). Analysis of a 20-span paper edit costs roughly $0.002 at current Haiku / GPT-4o-mini pricing.

Topics tab

What is the Topics tab?

The Topics tab analyses your transcript with AI to produce a structured map: broad themes broken down into specific subtopics, each with the transcript segments that cover it. It sits alongside Sources and Refine — click the Topics button above the paper edit panel to open it. It's designed for documentary and interview editing, where you need to understand what was said across many hours of rushes before you can start shaping a structure.

Topics, Emotions, and Story Beats — what's the difference?

A switcher at the top of the Topics tab lets you generate three different kinds of map from the same transcript: Topics (themes and subtopics), Emotions (emotional moments), and Story Beats (narrative structure). Each is generated, searched, and added to the paper edit exactly the same way — switching kind just changes what the AI is asked to find. Each source keeps a separate map per kind, so generating one doesn't affect the others.

How do I generate a topic map?

Open the Topics tab and click "Map topics" (or "Map emotions" / "Map beats", depending which kind is selected) on any source card. The AI reads the full transcript and returns a two-level hierarchy in a few seconds. It requires an AI key saved in Settings — the same key used for AI search in the Sources tab. Generation costs roughly $0.01–0.03 per transcript at current provider pricing.

What does the topic hierarchy look like?

Each source gets its own collapsible card. Click a topic row to expand it and see its subtopics. Click a subtopic to expand the individual transcript segments assigned to it. Topics are labelled in short, editor-friendly title-case names (e.g. "Career Beginnings", "On Collaboration"). Each subtopic includes a brief description of what was said. For multi-speaker sources, each segment shows the speaker's name.

How do I add topic segments to my paper edit?

Click the + icon next to any individual segment inside a subtopic to add it to your paper edit — it switches to a green tick. Click the count button next to a subtopic's name (e.g. "+ 4") to add every not-yet-added segment in that subtopic in one go; once they're all added it shows a tick instead. There's no single button to add an entire top-level topic at once — add subtopic by subtopic, or use the block count to gauge how much a topic covers before committing to it all.

Are added segments labelled automatically?

Yes. Whether you add one segment or a whole subtopic at once, the resulting block is labelled with its subtopic's name — for example "First Job in TV". You can edit or remove the label in the paper edit panel as normal. This works the same whether the source is a normal transcript or a "Selects" (derived) column.

What is the "Across sources" section?

When you've generated maps for two or more sources and the AI identifies that the same broad topic appears across multiple sources — e.g. both interviewees discuss "Creative Process" — that topic appears in the "Across sources" section at the top of the Topics tab. Each entry shows how many sources cover it and how many segments exist across them. Expand it to see a row per source (with the normal per-subtopic add controls), or use the group's own add-all button to add every not-yet-added segment from every source in one action.

How does cross-source grouping work? How does the AI know two topics are the same theme?

The extraction prompt instructs the AI to assign a consistent category slug (e.g. career_beginnings) to topics that cover the same theme, even if they are named slightly differently across sources. The app groups by that slug, client-side — no extra AI call. If two sources both contain a career_beginnings topic, they appear together in the Across sources section.

How do I search topics?

Use the search bar at the top of the Topics tab (visible once any source has a map for the selected kind). Typing filters the hierarchy live, keeping its normal nested topic → subtopic structure — matching any word in the topic name, subtopic name, or subtopic description. This is a plain local filter, not an AI search; there's no separate AI-powered topic search.

Can I export a topic map?

Click the "txt" button in a source's header to download every topic currently generated for that source (for whichever kind — Topics/Emotions/Story Beats — is selected) as a single plain-text file, with each subtopic's description and segment text/timecodes. There's no per-topic export, and no JSON/Paper-Edit export from this tab — to build a paper edit from topic segments, add them individually (or via a subtopic's add-all) as described above, then export or build from the paper edit panel as normal.

Can I regenerate a topic map after editing the transcript?

Yes — click "Regenerate" (the same button that said "Map topics" before a map existed) in the source header to run a fresh analysis; the old map is replaced. There's no automatic warning if the transcript has changed since the map was generated, so it's on you to remember to regenerate after a significant edit. Segments you've already added to your paper edit are not affected by a regeneration.

Does the Topics tab require an AI key?

Yes — generating a map (any of the three kinds) requires an AI key saved in Settings → AI API Keys. Text search (live local filtering) works without a key.

Multi-source projects

How do I work with multiple cameras or interviews?

In the Bridge panel, tick every sequence you want (the Sequences checklist supports multiple — see "Can I add several sequences at once?" below), pick the existing project in the Send to dropdown, and click Add sources. Each source gets its own transcript column, colour-coded (up to 8 colours: green, blue, orange, purple, teal, rose, amber, indigo) so you always know which camera or interview a line came from. Each column header shows a source picker — a dropdown showing the source name and its position (e.g. 1/3) — so you can see at a glance which source is loaded and switch to another without losing your scroll position.

Can I add several sequences at once?

Yes. The Bridge panel's Sequences field is a checklist, not a single picker — tick as many sequences as you want (or click "Select all") and click Add sources once. The currently active sequence is ticked by default, so a one-click add of just that one still works exactly as before; untick it if you don't want it included. Each ticked sequence is still sent and validated as its own separate upload, one after another — batching doesn't change the per-sequence size limit, so the "about 3 hours of transcribed audio" rule of thumb (see "Ingest failed (413)" below) still applies to each sequence individually, not to the batch as a whole. If one sequence in the batch fails or is a duplicate, the rest still go through — you'll see a summary like "Added 3 · 1 already present" when it's done.

How does the project layout work with multiple sources?

Transcript columns sit in a scrollable area to the left, with the paper edit panel fixed on the right. You can have up to four columns open at once — use the Column button in the controls row (above the transcripts) to add more. Each column has a source picker in its header (click it to switch which source that column shows, or move it left or right) and, next to it, a small ⊗ icon to close that column — this only removes it from your current view, it does not touch the underlying source or any of your selections. The paper edit panel stays fixed while you scroll.

How do I delete a source entirely?

Click the source picker in the column header, then "Delete source" near the bottom of the dropdown. This is different from closing a column (the ⊗ icon) — deleting removes the source and every block built from it, everywhere in the project, and can't be undone. You'll be asked to confirm first. Owners only.

How do I reorder transcript columns?

Click the source picker in any column header, then choose Move left or Move right from the dropdown menu. This is a local display change — it doesn't affect the underlying source order or any existing selections.

Can I rename a source?

Yes. Click the source name in the transcript column header to edit it inline. Type the new name and press Enter (or click away) to save. Renaming is safe — it only changes the display label. All clip matching, timecodes, and exports use internal IDs, not the name.

Can I add a source to an existing project?

Yes. In the Bridge panel in Premiere, tick the sequence(s) you want to add, choose the existing project in the Send to dropdown, and click Add sources. The new transcript column(s) appear in the browser immediately — no files to export or upload.

Can I bring in comments from a Frame.io review?

Yes. In Frame.io, export your review's comments as a CSV (from the review link, comments panel → export). In Paper Edit App, click the source picker in the column header for the matching footage, then "Import Frame.io comments…", and paste the CSV contents or pick the file. Each comment lands at the right point in that source's transcript, whether or not that bit of footage is in your paper edit yet — it shows as a small note pinned to the word it was made on. If you later add that word to a block, the same comment appears in the block's marker row too, and it becomes a real marker in Premiere when you build, exactly like a marker you'd placed by hand. Re-uploading the same export later (e.g. after more review comments come in) updates existing ones instead of duplicating them. Owners only.

What if my new source has a different frame rate or resolution to source 1?

Open the Sequence Settings dialog (next to the Export button) — if your sources differ, it flags the mismatch with an amber warning and lets you choose how the built sequence should be set up: match a source, or pick your own frame rate and resolution. Your choice is saved to the project and honoured by the Bridge when it builds; Premiere conforms off-rate clips to the chosen sequence rate.

Can I mix sources in one paper edit?

Yes. Select blocks from any column in any order. The export will cut between sources according to your paper edit order, not the original source order.

Does it support Premiere multicam sequences?

Yes. If your sequence contains a multicam source sequence — even inside a bin folder — the Bridge finds it and places it in the built sequence. One manual step is required after the build: select all clips in the new sequence, right-click, and choose Multi-Camera → Enable. This restores camera-switching — the timecodes and selections are already correct.

Does it handle multi-track audio?

Yes. If your source sequence has multiple audio tracks — stereo pairs, dual-mono, or multi-channel recordings — the Bridge places audio on the correct tracks in the built sequence, with video and audio correctly linked.

I have a multi-camera interview with a separate audio track per person — should I transcribe every track?

No — only transcribe one track per conversation. Transcribing every isolated mic (or both channels of the same stereo recording) sends the same conversation to Paper Edit App multiple times over, which does nothing for your paper edit but can be enough on its own to trigger the upload size error below on a long sequence.

In Premiere, run Window → Text → Transcript → Transcribe Sequence only on the one clip (or stereo pair, picking just one channel) that has the cleanest recording of everyone speaking — ideally one with Premiere’s multi-speaker detection so each person still gets their own speaker label in the transcript. Leave the other camera angles and isolated mic tracks untranscribed; the Bridge still places all of them correctly when it builds the final sequence, since build reconstructs every track regardless of which one was transcribed.

Rule of thumb: a single transcribed track of up to about 3 hours sends reliably. That 3-hour budget is a total across every track you’ve transcribed, not per track — three isolated mics transcribed on the same 90-minute conversation adds up to 4.5 hours of transcribed audio, not 90 minutes, and is likely to hit the limit below.

With only one mic transcribed, how do I know which file a column's transcript actually came from?

Look at the meta line in the column header, next to the duration — it names the source file directly (e.g. "INT_MicB.wav") when the whole column comes from one clip, which is the normal case for a single transcribed track. If a source is spliced together from several separate takes or files, the header instead shows a count (e.g. "3 files"), and a subdued divider with the file name appears in the transcript itself at each point the clip actually changes. This is the quickest way to confirm exactly which physical file to open in Premiere if you want to fix a diarisation error at the root instead of using Split (above).

Speakers

How do I get speaker labels in my transcript?

They come through automatically. When you transcribe your clips in Premiere (Text panel → Transcript), Premiere assigns speaker labels — the Bridge sends them along with the words, and they appear on every paragraph in Paper Edit App. If Premiere has speakers wrong, you can rename, reassign, or merge them here (see below) without touching the Premiere transcript.

What are the speaker colour tints?

Each speaker in a multi-speaker transcript is assigned a distinct opacity of the source's colour — up to four speakers, from lightest to strongest tint. The tint appears as the background of each transcript block and on the speaker chip, so you can see at a glance who is speaking without reading the name. Speakers are assigned tints in the order they first appear in the transcript. Tints work in both light and dark mode.

How do I filter the transcript to one speaker?

Click a speaker chip in the transcript header (the row below the block count). The transcript shows only that speaker's segments, and search and AI search operate only within those results. Click the same chip again, or click All, to return to the full transcript.

How do I rename a speaker?

Double-click a speaker chip in the transcript header. The chip becomes an editable field — type the new name and press Enter, or click away to save. The name updates across every transcript block and in the paper edit panel. Renaming is non-destructive: it stores a mapping on top of the original Premiere label, so you can rename again at any time.

How do I reassign one paragraph to a different speaker?

Right-click the speaker name above a transcript paragraph to open the reassign menu (this is separate from right-clicking a speaker chip, which reassigns everyone with that label — see "How do I merge two speakers into one?" below). Pick the speaker you want that one paragraph assigned to. The change is a per-paragraph override — it doesn't alter any other paragraph or the original Premiere labels, even ones that share the same original speaker. If the paragraph already has an override, the menu also offers "Reset to original". Not available on a "Selects" column, since that's a read-only view of a saved version rather than a live source.

Premiere missed a speaker change partway through a paragraph — can I fix just part of it?

Yes. Right-click the speaker name above the paragraph and choose "Split — reassign part of this paragraph…". Drag across just the words that belong to the other speaker, then pick who they should be reassigned to. The paragraph splits into pieces around your selection — the words before and after stay with the original speaker, only the ones you dragged over move. This is for when Premiere's own diarisation missed a speaker change entirely inside one continuous segment (so there's no existing paragraph break to reassign) — if the range you drag crosses more than one source clip, you'll be asked to keep it within a single clip.

How do I merge two speakers into one?

Right-click a speaker chip in the transcript header to open the bulk reassign menu. Pick the speaker you want all those segments moved to — every block currently attributed to that speaker is reassigned in one step. This is useful when Premiere has split one person across multiple speaker labels. The merged-from speaker disappears from the header once there are no segments left attributed to it. Like individual reassignments, this is an override — it doesn't alter the original Premiere labels.

Sharing with a producer

How do I share a project with a producer or director?

Open the project and click the Share button in the top right. Enter their email address and click Invite. They'll receive an email with a link to create their account and access the project.

What if the producer is already logged in to the app?

They don't need to click the email. As soon as you share, a notification appears in the bell icon in the top nav. Clicking it automatically accepts the invite and takes them straight to the project — no email link required.

What can a shared user do?

They have access to the full paper edit workflow: viewing transcripts, making selections, reordering spans, labelling them, and using the Topics and Refine tabs. Their edits sync live with yours, and they can leave comments and propose suggestions on any block (see "Working together" above). They can also rename speakers, reassign individual segments, bulk-merge speakers, and save or load paper edit versions — useful if Premiere's auto-detection needs correcting, or they want to check out a previous cut. AI search, AI topic mapping, and the Refine tab all work if they have saved their own AI key in Settings. When their edit is ready, they can click Sign off to tell you it's final and ready to build, click Request review for feedback mid-process, or post a comment. They cannot add, rename, or delete sources, cannot export in any format, and cannot see any of your other projects.

Where do I see projects that have been shared with me?

Shared projects appear alongside your own on the main Projects page, under a "Shared with you" section — there's no separate dashboard. It shows only the projects shared with you; your editor's other projects are not visible.

What happens when a producer is done with their edit?

They click Sign off (final, ready to build) or Request review (still want your input) in the project header. Either way you'll receive a notification in the bell — click it to open the project and pick up their edit. From there you can review their changes, export the paper edit, and build the sequence in Premiere via the Bridge panel.

Can a producer leave a project?

Yes. From within the shared project, there's a Leave Project button. Once they leave, they no longer have access.

How do I invite a new editor or producer to Paper Edit App?

On your projects dashboard, click "Invite an editor" (or "Copy invite link" in the banner). This copies a personal invite URL to your clipboard. Anyone who follows that link can sign up and their first project is free. The link is yours and multi-use — you can share it anywhere. It stays active until you generate a new one.

Does the producer see a help guide when they first open a shared project?

Yes. A Quick guide overlay appears automatically the first time they open the project. It walks through the three core actions: clicking a block to add it, Shift-clicking to select a range, and dragging to reorder with Cmd+Z to undo. Once dismissed it won't show again for that project, but they can always re-open it by clicking the Quick guide link in the project header.

Exporting

How do I get my paper edit back into Premiere?

In the Bridge panel in Premiere, choose the project and click Build Paper Edit. The panel pulls your paper edit and builds the sequence directly from the media already in your project — trimmed clips in order, video/audio linked, labels and notes placed as timeline markers. Nothing is exported, uploaded, or re-imported.

What is the Paper Edit JSON export for?

Click Export → "Paper Edit JSON" to download a file describing your edit — block order, word ranges, timecodes, labels and notes. It's a portable record of the edit: useful as a backup, for support requests, or for building your own tooling. The Bridge itself doesn't need it (it pulls your edit directly).

How do I control the sequence frame rate and resolution?

For single-source projects the build inherits everything from the source — no action needed. For multi-source projects, open the Sequence Settings dialog (next to the Export button) to choose: match a source, or pick your own frame rate and resolution. If your sources differ, the dialog flags it with an amber warning — Premiere will conform off-rate clips to your chosen sequence rate. Your choice persists for the project and is honoured by the Bridge build.

Can I print my paper edit or save it as a PDF?

Yes. Click Export → "Print / Save as PDF". Your browser's print dialog opens — choose "Save as PDF" as the destination to export a clean document. Only the paper edit panel prints: transcript columns, buttons, drag handles, and search controls are all hidden. Each block shows its timecode and transcript text; labelled spans show their label. All spans expand automatically for printing and return to their previous state when you close the dialog. A "Made with Paper Edit App" footer is added at the end.

After building with the Bridge, my multicam clips are not enabled for camera-switching — is that normal?

Yes — Premiere’s scripting API does not allow a panel to enable multicam mode automatically. The Bridge places clips with correct timecodes, then shows a tip in its log. To finish:

  • Select all clips in the new sequence
  • Right-click → Multi-Camera → Enable

Camera-switching is then fully active.

The Bridge says a clip was not found, even though it's in my project.

The Bridge re-finds clips through the source timeline they came from. If a clip is reported missing:

  • Check the source timeline still exists in the project (it must appear in the panel’s sequence picker)
  • If you renamed or replaced the source timeline since sending, re-send it as a source and re-select the affected blocks
  • Retry the build

The Bridge panel doesn't appear in Premiere — what's wrong?

The panel lives under Window → UXP Plugins → Paper Edit Bridge (not Window → Extensions). If it isn’t listed:

  • Confirm the install completed in Creative Cloud Desktop (requires Premiere Pro 25.6+), or unzip the .ccx and load its manifest.json with Adobe’s free UXP Developer Tool (Add Plugin → Load — Add Plugin only accepts a manifest.json, not the packaged .ccx itself)
  • Restart Premiere Pro after installing

Full instructions are on the Bridge page.

Account & settings

How do I set my display name?

Go to Settings → Display Name. Your name appears in notifications and shared project messages instead of your email address, so collaborators see 'Jane has shared…' rather than a raw email.

How do I change my password or email?

Go to Settings (link in the top nav). You can change your password (requires your current password) and update your email address.

How do I get an Anthropic (Claude) API key?

1. Go to console.anthropic.com and sign up or log in — this is separate from a normal claude.ai account. 2. Under Settings → Billing, add a payment method. There's no subscription — you're billed monthly for exactly what you use, and most editors spend well under $1 a month on this app's AI features (see cost breakdown below). 3. Under Settings → API Keys, click "Create Key" and give it a name (e.g. "Paper Edit App"). 4. Copy the key — Anthropic only shows it once — and paste it into Paper Edit App's Settings → AI API Keys. That's it; no further setup needed. If you'd rather not add a card yet, Gemini via Google AI Studio has a genuinely free tier and works everywhere Claude does in this app.

How much does AI actually cost to run?

You're billed by the provider directly, at their normal rates — there's no markup. Rough costs at current pricing: an AI search on a 500-block transcript is under half a US cent; a Refine pass over a 20-span paper edit is about $0.002; generating a topic map is $0.01–0.03 per transcript. A typical documentary project — regular AI search while editing, a handful of topic maps, a few Refine passes — comes to well under $1 in total, often just a few cents. There's no minimum spend and no wasted cost if you stop using it.

How do I organise projects into folders?

Click "New Folder" from your projects page to create a folder. Move a project into a folder using the three-dot menu on its card. Use the search box in the header to find projects by name across all folders.

Troubleshooting & error messages

"A block must be within a single clip. Select inside one clip."

Your drag started in one clip and ended in a different one. Each block's timecodes are relative to a single clip's media, so spanning two clips would misplace it when the Bridge builds the sequence. Release and try again, keeping your drag within one clip. Clip boundaries appear as paragraph breaks in the transcript.

"Couldn't save that change — it's been undone."

A network error prevented the last change (create, reorder, label, delete, etc.) from reaching the server. The UI has already rolled it back to the previous state. Check your internet connection and try again. If it keeps failing, reload the page — your last successfully saved state will load.

"Failed to add block."

The server couldn't create the block from your selection. This is usually a transient network error. Try the selection again. If it persists, reload the page.

"Couldn't apply the edit."

Word removal (pencil / inline edit mode) failed to save. The block has been left unchanged. Check your connection and try again.

"Couldn't reach the server. Reload to re-sync."

An undo or redo couldn't reach the server. Reload the page — your last saved state (including any collaborators' changes) loads from the database, and you can re-apply anything you wanted to keep.

"Couldn't post that comment." / "Couldn't post that suggestion." / "Couldn't update that comment."

A network error stopped a comment or suggestion from saving. Nothing is lost on your side — check your connection and try again. If it keeps failing, reload the page; existing comments and suggestions reload from the server.

"Couldn't apply that suggestion — the target block may have changed."

You accepted a suggestion, but the block it targets has since been edited or deleted (often by a collaborator), so the proposed change no longer fits. The suggestion is left open rather than applied. Review the block as it stands now and edit it directly, or reject the suggestion.

"Add an AI key in Settings to generate topics." / "Add an AI key in Settings to use Refine."

The Topics and Refine tabs require an AI API key (Claude, OpenAI, or Gemini). Go to Settings → AI API Keys, paste a key, and mark it active. Gemini via Google AI Studio is free and takes about two minutes to set up.

"Couldn't generate topics." / "Couldn't analyse the paper edit."

The AI call failed. Most likely causes: your API key has been revoked or run out of credit, the AI provider is temporarily down, or your key's rate limit was hit. Check that your key is valid in Settings, wait a moment, and try again. If the provider is having an outage, switching to a different active key (e.g. from Claude to OpenAI) will work around it.

Bridge: "No transcript found on this sequence."

Premiere hasn’t transcribed the clips in this sequence, or the transcription hasn’t completed yet.

  • In Premiere, open Window → Text → Transcript
  • Click Transcribe Sequence
  • Wait for it to finish (words will appear in the panel)
  • Click Send again in the Bridge panel

Bridge: "Your plan's project limit is reached — upgrade or reuse an existing project."

Your current plan allows a set number of projects. Either delete projects you no longer need from the dashboard, or upgrade your plan from Settings → Account.

Bridge: "Ingest failed (413)"

413 means the sequence you sent is too large in one go — almost always because more audio has been transcribed than actually needs to be. The size is driven by total minutes of transcribed audio, not the length of your sequence: transcribing the same conversation on several tracks (isolated mics, both channels of a stereo pair, multiple camera angles) multiplies the data for no benefit, since it’s the same words each time.

“Ignore Transcript” does not fix this. It only tells Premiere’s own caption/speech features to disregard that track — the transcript stays attached to the clip and the Bridge will still send it. Premiere has no way to detach or delete a transcript from a clip in place (the Text panel’s … menu only offers Re-transcribe, Export, and Import — nothing removes one).

  • The only real fix for a track you don’t want transcribed: re-import that media and replace the clip on the timeline with the fresh copy. This loses that clip’s transcript entirely, so only do it to tracks whose transcript you don’t need — see “should I transcribe every track?” above for which one to keep
  • As a rule of thumb, a single transcribed track of up to about 3 hours sends reliably — that budget is a total across every transcribed track in the sequence, not per track
  • Re-send from the Bridge panel

Bridge: "Open a Premiere project first."

The Build button was clicked but no Premiere project is open. Open the .pproj file that contains the media you sent, then click Build again.

Bridge: "Sent from [project], but a different Premiere project is open (media may be offline). Click Build again to build anyway."

The sequence you're trying to build was sent from a different Premiere project than the one currently open. If you click Build again, the Bridge will proceed but some clips may be offline (shown in red) if the media isn't in the current project's bin. To avoid this, open the correct .pproj file first, then click Build.

Bridge: connection or build fails with no clear message

  • Check that you’re connected — the panel shows your name and a Disconnect button at the top
  • If disconnected, reconnect using your Bridge key from Settings → Bridge Connection
  • If connected but builds fail, open the UXP developer console: Premiere → Window → Extensions → UXP Developer Tools
  • Look for [bridge] log lines — these show exactly where the build stopped and what Premiere returned

The Pauses toggle does nothing

Premiere only flags filler words when the transcript was created with filler-word detection turned on. To fix it:

  • In Premiere, open Window → Text → Transcript
  • Click the ••• menu and choose Transcript view options…
  • Enable filler-word detection
  • Re-transcribe the sequence
  • Re-send from the Bridge panel

A block shows no text (appears empty)

This can happen if a word-removal edit left a run containing only empty punctuation tokens from the Premiere transcript. Delete the empty block using its trash icon — it can't be edited or filled in after the fact. Future edits will not produce empty blocks.

Still stuck?

Send us a message and we'll get back to you.