More Prompts:
Suno for genre exploration using mood transitions →Suno using voice synthesis →Suno using music production →Suno for songwriting using storytelling techniques →Suno for mashups using Audio layering strategies →Suno for genre exploration using tempo shifts →Suno AI for jingles using specific genres →Suno AI for music generation using dynamic soundscapes →Suno AI for music generation using AI-driven remixing →Suno AI using personalized soundscapes →
Best prompts for Suno using podcast editing
Twelve practical, copy-ready prompts to use with Suno for common podcast editing tasks: noise reduction, EQ, normalization, chaptering, social clips, ad insertion, transcription, mastering, and more. Each entry includes a concise explanation and a realistic example you can paste and run.
Claude Opus 4
Gemini 2.5 Pro
GPT-5
Claude Sonnet 4
Gemini 2.5 Flash
You've got great podcast content, but your raw recordings sound like they were captured in a tin can during a thunderstorm. Hours disappear as you manually hunt through audio files, tweaking EQ settings and wrestling with noise reduction while your publishing deadline looms closer. Every podcaster knows this frustration: having brilliant conversations trapped inside mediocre audio that makes listeners hit skip.
These twelve battle-tested Suno prompts transform your chaotic post-production workflow into a streamlined powerhouse that handles everything from noise cleanup to final mastering. Whether you're dealing with remote guest audio that sounds like it came from different planets or need to generate social clips that actually get shared, each prompt gives you the exact language to get professional results fast. Stop spending weekends buried in audio editing software and start publishing podcast episodes that sound as good as your ideas deserve.
1
Remove noise, hum, and room reverb
Edit file: episode_raw.wav. Remove steady electrical hum at 60 Hz and its harmonics (60/120/180 Hz). Apply broadband noise reduction to reduce hiss without causing metallic artifacts - target 6–10 dB reduction in noise floor. Apply light dereverb to reduce room tail by ~30% while keeping natural sibilance. Preserve vocal clarity and do not alter sections labeled 'music' (00:05:10–00:06:00). Output high-quality WAV 48 kHz 24-bit and a backup MP3 192 kbps.
Clean a raw recording by removing constant hum, broadband noise, and reducing room reverb while preserving natural voice tone.
2
Dialogue EQ and de-essing for two-speaker interview
Edit file: interview_raw.wav. Detect speaker sections (Host labeled H, Guest labeled G) or use channel separation. For Host: apply high-pass at 80 Hz, gentle presence boost +2.5 dB at 3–5 kHz, cut 200–300 Hz -1.5 dB if boxy. For Guest: high-pass at 100 Hz, boost +1.5 dB at 4 kHz, reduce harshness by -2 dB at 6–8 kHz. Apply de-esser thresholds to reduce sibilance peaks by 4–6 dB only when S > -6 dB. Keep natural breath and vocal dynamics. Export WAV 48 kHz 24-bit.
Apply different EQ/de-essing profiles for host and guest to balance tone and tame sibilance without over-processing.
3
Remove filler words and long pauses
Edit file: episode_edit.wav. Detect filler words 'uh', 'um', 'you know', 'like' when they are shorter than 700 ms and remove them entirely. For pauses >1.2 seconds, shorten to 700 ms unless pause falls inside a quoted passage or emotive moment (mark timestamps manually: 00:18:30–00:18:45 emotive). Keep a 5 ms crossfade to avoid clicks. Produce two versions: conservative (only remove fillers <400 ms) and aggressive (remove up to 700 ms). Export conservative_version.wav and aggressive_version.wav.
Automatically cut or shorten filler words (uh/um/you know) and trims long silent gaps while preserving natural pacing, with an allow-list around 1–1.2 seconds for intentional pauses.
4
Loudness normalization and final limiter
Edit file: final_mix.wav. Normalize integrated loudness to -16 LUFS (podcast standard) and true-peak to -1.0 dBTP. Use gentle RMS/peak limiting with attack 5 ms, release 100 ms, gain staging to avoid pumping. Apply optional loudness +3 dB preview for platforms that prefer higher levels. Export final_master.wav (48 kHz/24-bit) and final_master_128kbps.mp3.
Bring the episode to target broadcast loudness and apply a transparent brickwall limiter for consistent perceived volume across episodes.
5
Automatic chapter markers and timestamps
Analyze episode_clean.wav and create chapter markers. Identify: intro (0:00–0:45), topic 1 (0:45–11:20), ad break (11:20–12:00), topic 2 (12:00–28:45), mid-roll music (28:45–29:05), Q&A (29:05–38:00), outro (38:00–39:20). Output a JSON array of chapters with start time, end time, title (max 40 chars), and 1–2 sentence summary for each chapter. Prefer human-readable timestamps (mm:ss) and include suggested chapter artwork if music-heavy.
Generate chapter markers by detecting topic changes, ad breaks, and music cues with precise timestamps and short titles for RSS embedding.
6
Generate show notes and episode summary
Create show notes for episode_clean.wav and its transcript. Provide: 1) 2–3 sentence episode summary, 2) five key takeaways (bulleted), 3) guest bio (50–70 words), 4) list of links/resources mentioned with timestamps, and 5) three social media captions of 120–200 characters each. Use natural language, include relevant keywords (AI audio, podcast editing), and format timestamps as mm:ss.
Produce SEO-friendly show notes: 1-paragraph summary, 5 bullet highlights, guest bio, resources/links, and 3 suggested social captions.
7
Create short social audio & video clips
From episode_clean.wav, detect 3 high-energy moments suitable for social: Clip A (00:06:20–00:07:05), Clip B (00:21:10–00:21:50), Clip C (00:33:05–00:33:45). For each clip: remove long pauses, apply a 1.5–2 dB vocal boost at 3–5 kHz, add soft instrumental bed at -18 dB, and 0.5 s fade in/out. Produce audio clips (wav and mp3) and 1080x1080 video files with auto-generated captions and waveform overlay. Name files clipA_30s.mp4, clipB_40s.mp4, clipC_40s.mp4.
Extract high-impact clips (30–60s) with clean edits, background music, and optional auto captions for social sharing.
Stop Losing Your AI Work
Tired of rewriting the same prompts, juggling ChatGPT and Claude in multiple tabs, and watching your best AI conversations disappear forever?
AI Flow Chat lets you save winning prompts to a reusable library, test all models in one workspace, and convert great chats into automated workflows that scale.
“AI Flow Chat powers our entire content strategy. We double down on what’s working, extract viral elements, and create stuff fast.”
Reference Anything
Bring anything into context of AI and build content in seconds
YouTube
DOCX
TikTok
Web
Reels
Video Files
Twitter Videos
Facebook/Meta Ads
Tweets
Audio Files
Choose a plan to match your needs
Upgrade or cancel subscriptions anytime. All prices are in USD.
Nano
Start your AI journey with a 14-day free trial, then continue for just $8/month.
$0for 14 days
then $8 /month
- Free for 14 days - cancel anytime
- 500 credits per month
- Access to all AI models
- Free optional onboarding call
- 1,000 extra credits for $6
Start Free Trial
No risk, cancel anytime.
BasicRecommended
For normal daily use. Ideal for getting into AI automation and ideation.
$30/month
- See what Basic gets you
- 11,000 credits per month
- Access to all AI models
- 5 app schedules
- Free optional onboarding call
- 1,000 extra credits for $6
Get Started
No risk, cancel anytime.
Pro
For power users with high-volume needs.
$100/month
- See what Pro gets you
- 33,000 credits per month
- Access to all AI models
- 10 app schedules
- Remove AI Flow Chat branding from embedded apps
- Free optional onboarding call
- 2,000 extra credits for $6
Get Started
No risk, cancel anytime.
Frequently Asked Questions
Everything you need to know about AI Flow Chat. Still have questions? Contact us.