How to Overdub a Line in Descript

Most “overdub a line in Descript” posts still write to a button that is not on the toolbar. Overdub is the search. The published control in 2026 is Regenerate — type the correction, generate a new take in an authorized clone of that speaker, preview it in the sentence it has to sit in. This guide is that working path — consent, speaker, highlight, type, preview — using the one editor we send for this brief: Descript.

When a one-line replace is the job — and when you should re-record instead

Use this pass when the words are almost right. A date you flipped, a guest’s name you clipped, a product you called the old name: the rest of the take is the show. You do not want a new booth hour. You want that sentence said correctly in a voice that still sounds like the person who sat in that room. Regenerate is the published control for that. A custom AI Speaker is the published voice. Consent is the published gate.

Skip this pass if the remaining job is the radio edit. Deleting the tangent at 18:40 is a sentence job, not a 250-character patch. That working path is How to edit a podcast in Descript — an ordinary guide link, not a second money hop. Skip both if the file still sounds like a kitchen: How to clean up podcast audio in Descript. Long gaps are How to remove silence in Descript. A usable transcript export is How to transcribe a podcast in Descript. Those pages hop to Descript too. This one already will.

Skip the clone entirely if you can say the line again in ten minutes on the same mic. A real pickup will match the room without a consent script. Skip Descript-as-narrator if you want a different voice on purpose. That is a voiceover desk — How to make a podcast intro with ElevenLabs or How to clone your voice for YouTube — ordinary site paths, not Try buttons here.

The seven-step Descript line replace

1. 01

   Confirm you own the voice — and that this line is yours to replace

   This pass is for a host line you said, or a voice the speaker has authorized you to clone. Guest likeness is not automatically yours to generate. Official AI Speaker help will not authorize a deceased person, a non-consenting speaker, someone who cannot record the training statement, or audio that already came from an AI. Put clone-and-replace rights in the guest release if a guest is the one who flubbed the line. If you do not own the voice, stop. Re-record, or leave the take.

2. 02

   Open the composition that already has the take — not a blank Write-mode script

   Regenerate (the current public name for the job people still search as Overdub) replaces words on a recording you already have. Open the episode project and the composition that holds the cut. If the file is not in yet, import from your computer, from Zoom if that is the source, or from a phone upload. Transcription starts after the file lands. Wait for the script. A file sitting only as a layer is not a transcript — official add-a-file help says only script media is transcribed. Do not start a new composition in Write mode and type a whole narrator. That is generate text-to-speech, a different brief.

3. 03

   Assign the speaker, then train or pick an authorized custom AI Speaker

   Official Regenerate help: to replace what was said, the original speaker must have a custom AI Speaker created and authorized, and that speaker must be assigned on the script. Label the host first — Identify speakers after detection, or type @ / Change speaker. Then create or pick the voice. Official create-AI-Speaker path: Add speaker → Create speaker → name it → open the speaker’s … menu → Enable speech generation. That opens the consent and authorization script. Record it in English, on the same mic you used for the episode if you can. Speak naturally. Submit. Overview copy says a custom AI Speaker can train from as little as 30 seconds. If the host already authorized a clone on this Drive, pick that speaker — do not train a second one “just in case.” Stock AI speakers are for writing a new voiceover. Official replace-what-was-said help does not treat a stock voice as a substitute for an authorized custom clone on the original speaker.

4. 04

   Highlight only the misspoken line — stay inside one scene, under 250 characters

   Find the flub in the script. Highlight that phrase or sentence, not the paragraph around it and not the next scene. Official limits: each Regenerate action is capped at 250 characters; a selection that crosses a scene boundary or includes ignored text will not run; Regenerate needs original recorded audio on both sides of the selection — a patch sitting only between other AI clips will fail. If the remaining problem is a three-minute ramble, that sentence still has to leave on the radio-edit how-to. If the remaining problem is a fridge, that is Studio Sound, not a rewrite.

5. 05

   Open Regenerate, type the correction, generate the new line

   Official path: click Regenerate on the selection toolbar, or press D. A dialog opens with a text field. Type the words that should have been said. Then click Regenerate in the dialog. The script text pulses while it processes. Public 2026 help does not name a toolbar control called Speak for this job, and it does not name Overdub on the button — changelog copy is explicit that Overdub is now part of Regenerate. Some older silence-repair copy still says Replace → Regenerate; that is the same family of action when you are rewriting the words. On a video episode with a single script track, the control defaults to Audio & video. Open the caret next to Regenerate and choose Audio only if you only want the line, not a mouth-move. Sequences do not support video regeneration. English audio and video only on the published Regenerate page.

6. 06

   Preview so the new line matches the room — Play, Retry, or Restore

   Official Regenerate toolbar after the pass: Play (preview the regenerated section), Restore (revert to the original recording), Retry (another variation), Accept (keep it). Turn Play on before you Accept. Listen for a clone that jumped rooms — a drier booth than the kitchen-mic take, a brighter S, a cadence that no longer sounds like the sentence before it. Official pricing copy says Regenerate is meant to match the surrounding tone. The published way to check that is preview, not a room-tone slider we can confirm. Official troubleshooting: if the clone is wrong, create a new AI Speaker with a fresh recording on the usual mic; there is no way to add more samples to an existing AI Speaker. Artifacts usually came from the training take (traffic, appliances, music, mouth noise). Retry once or twice. If the third pass still sounds like a different room, Restore and re-record the line.

7. 07

   Accept, listen in the sentence before and after, then export if the episode is otherwise done

   Accept keeps the result. On video, official help clips the original picture to the regenerated section, moves it into the layer lane, and hides it. First-time video regeneration asks for a separate consent because it modifies a speaker’s visual performance. Then play the line in context — the breath before, the word after. Official AI-Speaker troubleshooting notes that generated speech often includes a little extra on either side for flexibility; convert the AI clip to an audio layer if you need to trim or crossfade like recorded audio. Official TTS help: timeline edits, fades, and precise playback want that conversion. Then Export → Local export if this was the last fix. Published audio formats are .m4a, .wav, and .mp3; video local export is MP4. Listen to the file that left the app. If you still need the radio edit, the cleanup, silence, or a transcript export, those are ordinary site paths — this page already hopped to Descript.

Regenerate vs re-record vs handing the sentence to a VO tool

“Overdub a line in Descript” is a search. The decision is whether this host, in this room, can be patched from typed text. The Descript column matches published Regenerate, custom AI Speaker, and consent help as of August 2026. Voiceover tools stay qualitative here — we already wrote those desks, and this page does not hop there.

Overdub, Regenerate, Speak, Replace — write to the control that exists

Descript’s changelog is the cleanest sentence we have: Overdub is going away as a label, and replacing your script with AI Speech is now part of Regenerate. Highlight a section, click Regenerate on the script toolbar. If you edit the text, you need voice authorization for that speaker — the same gate Overdub used, under a different name. We are not going to keep teaching a retired button.

Public 2026 help does not name a toolbar control called Speak for this job. The published neighbor is Generate text-to-speech: Write mode, assign an AI Speaker (custom clone or stock), click Done writing, and Descript generates a new voiceover. That is how you write an intro from scratch. It is not how you patch a line the host already said. If a third-party write-up still says Speak, the actions we can confirm are Enable speech generation, Generate text-to-speech, and Regenerate.

Replace is the verb, not a second product. Official Regenerate help: use it to replace or rewrite parts of your script with an authorized custom AI Speaker. Older silence-repair copy still points at Replace → Regenerate when you want a rough join smoothed. That second article — Use Regenerate to smooth or improve a section — is for when the words stay and the cut is ugly. Stay on change what was said when the words are the problem.

Train or pick the speaker — consent is the product

Official getting-started copy still gives you two starts: record in Descript, or import an existing file. Import paths they publish include upload from your computer, import from Zoom, and upload from a phone. Put the file in the script. Wait. Media minutes start when the file is in the project. Do not re-import an hour you already radio-edited “just to overdub one line.”

Label the person who misspoke. Automatic speaker detection can run on import; Identify speakers is the published follow-up. In the script, type @ or select text and Change speaker. Official Regenerate help will not rewrite the take until a speaker is assigned and that speaker has an authorized custom AI Speaker. A label that still says Speaker 1 is not a clone.

Official create path: Add speaker (usually at the top of the composition) → Create speaker → name it. Click the new label, find the name, open the … menu, choose Enable speech generation. That is the published action. It displays the consent and authorization script. Choose a microphone. Record. The statement must be read in English, even if you later generate non-English text-to-speech. Speak naturally, with varied tone — official copy says the delivery of that script shapes the clone. Review. Re-record if the take is noisy. Submit. Confirmation usually arrives within minutes. Overview copy: as little as 30 seconds of audio.

If the host cannot sit in the app, official help lets them send a recording of that same consent statement. You still run Enable speech generation, then choose the file at the bottom of the Train and authorize speaker window. That is the published collaborator path. It is not a loophole. The voice still has to be theirs.

Official list of voices they will not authorize: a deceased individual, a non-consenting speaker, someone unable to record the training and authorization statement, and audio originating from an AI or artificial source. Bypassing the process is a Terms of Service breach. We are describing their gate. We are not going to invent a “clone my guest from the ISO” button.

If that host already authorized a clone on this Drive, pick it. Assign that speaker. Do not train a second “better” one unless the first one failed a headphone pass — official troubleshooting is explicit that you cannot add more samples to an existing AI Speaker. A new speaker is a new recording, on the usual mic, in the tone you want (casual, formal). Stock AI speakers live on the same dropdown for Write-mode narration. They are not the published way to replace what this host already said.

Type the correction, generate, then preview in the room

Highlight the flub. Official run-through: Regenerate on the selection toolbar, or press D. A dialog opens with the current words. Type the phrase that should have been said. Click Regenerate. The script pulses while it works.

Official limits we will not sand off. Each action is 250 characters. A selection that crosses a scene boundary or includes ignored text will not run. Regenerate needs original recorded audio surrounding the selection — if the line is bordered only by other AI speech, or has no surrounding audio, it will fail. English only on the published Regenerate page. On video with a single script track, the default is Audio & video; the caret next to Regenerate switches to Audio only. Sequences do not support video regeneration — the Audio & video option stays gray until you are on a single script track and have given video-regeneration consent. First-time video regen asks, because it modifies a speaker’s visual performance. Official help will also refuse B-roll, multi-speaker recordings, and shots where the face is not clearly visible.

Then listen on purpose. Official toolbar: Play, Restore, Retry, Accept. Play the line in the sentence before and after it. Official pricing copy: Regenerate is meant to match the surrounding tone and smooth awkward cuts. That is the claim. The published check is your ears. There is not a public slider we can confirm named Room Match, Presence, or “make it sound like the kitchen.” If the clone is brighter, drier, or faster than the take it sits in, Retry. If the third variation still jumped rooms, Restore. Train a new AI Speaker on the episode mic if the clone was built in a different space — artifacts in official troubleshooting usually came from the training audio (static, traffic, appliances, music, mouth noise).

Accept keeps the result. On video, the original picture for that section is clipped, moved to the layer lane, and hidden. Official AI-Speaker troubleshooting: generated speech often includes a little extra on either side so you can trim the join. Convert the AI clip to a standard audio layer when you need word-boundary edits, fades, or a crossfade — official TTS help says AI speech is not recorded audio until you convert it. Do not run Studio Sound on the generated clip until that conversion; official cleanup help says the effect will not apply to generated speech until you do. Think twice even then — you are re-processing a voice that was never in that room.

Underlord can be asked to fix a line. Treat that like a junior editor who will also burn credits. Watch the same preview. Full Underlord access is a plan question on the August 2026 grid; we do not invent a checkout total.

Export the patched file — or stop and re-record

If this was the last fix, leave with a file. Official export overview: click Export, pick a destination. Local export writes a file you control. Published audio formats are .m4a, .wav, and .mp3. Video local export is MP4. Fill metadata when the format supports it; official help notes that .wav does not carry artwork or chapter markers. Descript does not mint your RSS URL. Upload the enclosure to the host that already serves the feed. We do not invent a host hop.

Official pricing copy on Regenerate: after you hit the specified limit, generated speech becomes “jibber” “jabber.” That is the published empty-tank sound, not a joke we added. Free-plan AI Speech, Regenerate, and custom voice clones are Limited on the August 2026 grid. Sit on a paid plan before the patched line is the one subscribers get. Confirm checkout on descript.com/pricing. We do not print a commission rate.

When the next job is the edit, the cleanup, silence, or a real voiceover

Stay here when one line is wrong and you own the voice. Hand the composition to the radio edit when a story still has to leave: How to edit a podcast in Descript. Hand it to cleanup when the room is the problem: How to clean up podcast audio in Descript. Hand it to the silence pass when the remaining problem is time between words: How to remove silence in Descript. Hand it to the transcript pass when you still need names and a text file: How to transcribe a podcast in Descript. None of those are Try buttons on this page. The only hop here is Descript.

A generated show open you will rewrite every season is How to make a podcast intro with ElevenLabs. A YouTube-channel clone is How to clone your voice for YouTube. The voice-tool scorecard is ElevenLabs vs Murf vs Synthesys. Finding 5–15 verticals in a finished episode is a clipper job — start at Descript vs Klap if you have not picked that stack yet. None of those names are hops on this page.

We do not print an affiliate commission rate, and we do not invent a “this will earn you $X” line. The product question is whether the patched line still sounds like the person in that room after you previewed it — and whether you were honest about the voices you do not own.