Step 1: Train Your AI Voice Clone

Before using Overdub, you need to create your AI voice model. Navigate to the Overdub section in Descript and click “Create a new voice.” You’ll be prompted to record a consent statement confirming you authorize the creation of your voice clone — this is a critical ethical safeguard. Then, upload at least 10 minutes of clean audio of yourself speaking, or record directly in the app. The more training data you provide, the more natural and accurate your voice clone will be. For best results, use audio recorded in a quiet environment with consistent microphone placement.

Step 2: Verify Your Voice Clone Quality

Once training completes (usually 10-30 minutes), test your voice clone by typing a few sentences in the Overdub panel and clicking “Generate.” Listen carefully for naturalness, pronunciation accuracy, and emotional tone. If the clone sounds robotic or mispronounces certain words, add more training data. Descript also allows you to create a custom pronunciation dictionary for words your clone struggles with.

Step 3: Identify Mistakes in Your Recording

Import your recording into a Descript project and let it transcribe. Read through the transcript and highlight any mistakes you want to fix — mispronounced words, incorrect facts, or awkward phrasing. Make a note of each correction needed.

Step 4: Apply Overdub Corrections

For each mistake, select the incorrect text in the transcript and type the correction. When you modify text that has corresponding audio, Descript will ask how you want to handle the change. Select “Overdub” and choose your trained voice from the dropdown. Descript generates the corrected audio in your AI voice and seamlessly blends it into the existing recording. The transition between original and Overdub audio is typically imperceptible for short corrections.

Step 5: Fine-Tune the Blend

For longer Overdub segments, the AI voice might sound slightly different from the original recording’s acoustic environment. Use Descript’s audio editing tools to adjust the volume, apply Studio Sound for consistency, and ensure the Overdub segment matches the surrounding audio. You can also add slight reverb or room tone to match the original recording’s characteristics.

Step 6: Batch Correct Common Errors

If you notice the same error recurring throughout your recording — perhaps you consistently said the wrong product name — you can use Descript’s find and replace feature to locate all instances and Overdub them in batch. This is significantly faster than correcting each occurrence individually.

Step 7: Export and Review

Always do a final listen-through of your entire recording after applying Overdub corrections. Pay special attention to the transitions between original and Overdub audio. If any segment sounds unnatural, you can undo the Overdub, adjust the text, and regenerate. Once satisfied, export your corrected recording.

Overdub is one of Descript’s most powerful and unique features. By eliminating the need to re-record for minor corrections, it saves hours of production time and removes the frustration of having to choose between perfection and efficiency. Use it responsibly, always disclose AI-generated voice segments when required by your platform’s policies, and enjoy the freedom to fix mistakes without starting over.

Step 1: Record Your Presentation

Use Descript’s built-in screen recorder or import a pre-recorded presentation video. If recording within Descript, click “Screen Record,” select your screen and camera layout, and start presenting. Descript captures both your screen content and camera feed simultaneously, then auto-transcribes upon completion.

Step 2: Transcribe and Identify Issues

Review the auto-generated transcript. Mark three categories of issues: (1) filler words like “um,” “uh,” “basically”; (2) factual errors or misstatements; (3) awkward pauses or tangents. Color-code these by highlighting with different marker styles in Descript.

Step 3: Batch Remove Filler Words

Click “Remove Fillers” for automatic filler word detection and removal. Descript identifies all common filler words across your entire presentation. Review the highlighted instances — you can keep intentional pauses and only delete true fillers. Confirm removal and Descript eliminates all selected fillers, creating a smoother flow.

Step 4: Fix Misstatements with Overdub

For factual errors or misstatements, use Overdub. If you said “2024 revenue was $$5 million” but meant$$50 million, highlight “5 million” in the transcript, type “50 million,” and Descript replaces the audio using your cloned voice. The correction sounds natural because it’s synthesized from your own voice pattern.

Step 5: Set Up Voice Cloning (First-Time Only)

If you haven’t created your Overdub voice clone yet, Descript guides you through recording a 10-minute voice sample. Read the provided script clearly and naturally. After processing (about 30 minutes), your clone is ready. Subsequent Overdub corrections work instantly with no additional recording.

Step 6: Smooth Out Abrupt Transitions

After deletions and replacements, some audio transitions may sound abrupt. Use Descript’s “Smooth” transition feature at edit points — it applies a brief audio fade that makes cuts imperceptible. For video edits, Descript applies subtle visual transitions to maintain continuity.

Step 7: Final Review and Export

Play back the entire edited presentation. Listen for any remaining issues — unnatural Overdub segments, choppy transitions, or content gaps. Make final adjustments. Export as MP4 video with embedded captions derived from your edited transcript. Upload to YouTube, LinkedIn, or your company platform.

ProTips:

• Record Overdub voice samples in a quiet environment for highest clone quality
• For short presentations, remove fillers manually to maintain intentional rhetorical pauses
• Export captions as SRT files alongside your video for accessibility compliance

Step 1: Import Your Raw Recording

Open Descript and create a new project. Drag and drop your raw audio or video recording file into the project. Descript supports MP3, WAV, MP4, M4A, and most common media formats. Once imported, Descript automatically begins AI transcription — this typically takes 2-5 minutes for a 60-minute recording.

Step 2: Review the AI Transcript

Once transcription completes, you’ll see a full text document on the left side of the screen, with the corresponding media timeline on the right. Read through the transcript to identify sections you want to cut — off-topic tangents, redundant explanations, awkward pauses, or factual errors.

Step 3: Cut Unwanted Content by Deleting Text

To remove a segment, simply highlight the unwanted text in the transcript and press Delete. The corresponding audio/video segment is automatically removed from the timeline — no manual scrubbing, no precise timestamp hunting. Delete multiple scattered phrases across the episode and Descript seamlessly stitches the remaining segments together.

Step 4: Remove Filler Words Automatically

Click the “Remove Fillers” button in the toolbar. Descript’s AI scans your entire transcript and highlights all filler words — “um,” “uh,” “like,” “you know,” “sort of.” Confirm the removal and Descript deletes every instance simultaneously. This single step typically saves 5-10 minutes per episode and dramatically improves listenability.

Step 5: Use Overdub to Fix Mistakes

If a speaker said something incorrect, instead of cutting the segment, use Overdub. Highlight the incorrect text, type the correct version, and Descript generates the corrected audio using the speaker’s cloned voice. First-time users need to record a 10-minute voice sample for cloning; after that, Overdub works instantly for any correction.

Step 6: Add Intro/Outro and Music

Import your podcast intro music and outro files as additional tracks in Descript. Drag them to the beginning and end of your timeline. Adjust volume levels using Descript’s multi-track mixer — duck the music volume when speech begins, and raise it back during transitions.

Step 7: Export Your Finished Episode

Click “Export” and choose your format — MP3 for audio podcasts, MP4 for video podcasts. Set quality settings (128kbps MP3 is standard for podcasts). Add episode metadata: title, description, chapter markers based on your transcript sections. Export and upload to your podcast hosting platform.

ProTips:

• Use keyboard shortcuts extensively — Ctrl+F to search transcript for specific words, making targeted edits fast
• Create chapter markers by inserting “Chapter” labels in the transcript; they export as podcast chapter markers
• Always review the edited audio by playing it back — text edits are precise but occasional transitions may sound slightly abrupt