Podcasting
Descript's September 17 update brings AI-generated music, sound effects, and 18 caption presets. Here's what podcasters and video creators get for $16/mo.
Some links are partner links: if you subscribe through them, we may earn a commission, at no extra cost to you. The crowd verdicts stay independent.
Descript now generates background music and sound effects directly inside the editor. The September 17, 2026 update adds AI audio generation that drops custom tracks onto the timeline at any length, plus a rebuilt captioning system with 18 presets and 15 text animations.
The quick take
Descript ($16/mo) now competes with dedicated AI music tools. Describe what you need, get a track. The crowd gives it a 57% recommend rate, strong for an editor-first tool.
What AI Audio Generation Actually Does #
The new feature lives in Descript's AI tools panel and through Underlord (the AI assistant). Type a description: "upbeat jazz background for a tech review intro, 30 seconds." The system generates audio and places it on the timeline at the requested length.
This covers three use cases:
| Use case | How it works | Who benefits |
|---|---|---|
| Background music | Describe mood, genre, tempo | Podcasters avoiding royalty issues |
| Sound effects | Request "whoosh," "doorbell," "knock" | Video editors needing quick SFX |
| Generic beats | Ask for rhythm tracks | YouTubers adding energy to cuts |
The implementation sits inside Descript's existing workflow. No separate tool, no export/import cycle. This matters because Descript's core value proposition is text-based editing: cut by deleting words in the transcript. Adding music generation keeps everything in one place.
How This Compares to Dedicated AI Music Tools #
Descript enters territory occupied by Suno, AIVA, and Beatoven.ai. The difference: those tools exist solely for music generation. Descript bolts audio generation onto an editor-first product.
For podcasters already paying $16/mo (Hobbyist plan) or $24/mo (Creator), this is free additional functionality. The pricing note from Descript's official page confirms: Hobbyist $16/mo annual ($24 monthly), Creator $24/mo annual ($35 monthly), Business $50/mo annual ($65 monthly). The question is quality. Descript's TTS voices "sound noticeably more robotic than ElevenLabs," according to the crowd consensus. Will AI-generated music follow the same pattern: functional but not premium? Early reports suggest the audio works for background use, not for tracks that need to carry a production.
Descript
All-in-one podcast/video editor with voice cloning bolted on, not a pure TTS tool
Partner link. The crowd verdicts stay independent.
The Caption Overhaul: 18 Presets and 15 Animations #
The second major addition is a rebuilt caption system:
- 18 new presets from Descript's design team
- 15 text animations (10 new, with separate in/out motion)
- Search and filtering in the preset list
- Redesigned properties panel
Captions matter for social clips. YouTube Shorts, TikTok, Instagram Reels: all favor burned-in captions. Descript now ships with more visual options out of the box, reducing the need to export to external tools.
Other September Additions Worth Noting #
The update includes smaller features that stack value:
- ElevenLabs voice library integration : access more voices beyond Descript's native 25+ options
- Convert recordings to AI speech : swap recorded audio for a selected AI voice
- Smooth all jump cuts at once : batch processing instead of one-at-a-time
- Schedule Rooms recordings without host : set up remote sessions that start automatically
- Skin smoothing effect : cosmetic video filter
- Google Drive import on web : finally available outside desktop
- Zapier connector : automation marketplace availability
The ElevenLabs integration is notable. Descript acknowledges its native voice clones "sound noticeably more robotic" and now offers access to a competitor's library. This suggests a pragmatic approach: own the editing workflow, partner for voice quality.
Descript
All-in-one podcast/video editor with voice cloning bolted on, not a pure TTS tool
Partner link. The crowd verdicts stay independent.
Should You Switch or Subscribe? #
Descript's 57% crowd recommend rate reflects its position: excellent for podcast/video editing, weaker as a standalone voice tool. The September update reinforces this identity. AI music generation adds convenience for creators already inside the ecosystem.
The verdict:
- If you already use Descript for editing, the update delivers real value at no extra cost
- If you need dedicated music generation, purpose-built tools like Suno or AIVA offer more control
- If you're comparing Descript to Podcastle (from $12/mo, 50% recommend rate), both now offer AI audio features inside editing suites
For a direct comparison of these podcast-focused tools, see the Descript vs Podcastle breakdown. And for the full picture of AI voice tools, the voice generator leaderboard ranks all 18 options by crowd score and value. Keep exploring
Every claim above is backed by the arena's live data: crowd votes, verified pricing, honest pros & cons.
More from the arena journal #
Podcasting
Descript Now Runs Claude Fable 5: What It Means for AI Podcast Editing
Descript's August 5, 2026 update adds Claude Fable 5 to Underlord chat. Here's what changes for podcast editors, plus scheduled Rooms and AI image editing.
Aug 12, 2026 · 4 min read
Podcasting
Descript vs Podcastle: The Real Cost Per Podcast Episode
Comparing Descript and Podcastle pricing beyond the sticker price: overage fees, feature tiers, and actual cost per finished podcast episode in 2026.
Jul 31, 2026 · 3 min read
Industry News
Can You Legally Sell AI Music From Suno and Udio in 2026
Complete breakdown of commercial licensing terms, ownership rights and monetization paths for AI-generated music across Suno, Udio, ElevenLabs Music and Stable Audio.
Aug 7, 2026 · 5 min read