Try “Veo”, “voiceover”, “thumbnail” or “Descript” · Esc to close

🎙️ Podcasts (Spotify, Apple)

Create podcasts for Podcasts (Spotify, Apple) with AI

Recording, editing, enhancing and repurposing podcasts. We ranked 16 apps that make it, favouring the ones built for Podcasts (Spotify, Apple), then grouped them into a stack you can actually use.

Typical shape on Podcasts (Spotify, Apple): audio episodes plus video clips for promotion.

Your stack, step by step

The strongest picks in each kind of tool that makes podcasts. Most creators combine two or three of these.

Tools that fit, ranked

1

ElevenLabs Freemium

Text to speech, voice cloning, dubbing, sound effects and licensed music in one studio

9.0/10

What it is ElevenLabs is a US/UK voice AI company whose creator suite (now branded ElevenCreative) turns text into speech, clones voices, dubs video into other languages, and generates sound effects and music. The same models are sold to developers through the ElevenLabs API, and the company also runs voice-agent products for businesses. Key features - Text to speech with… Read more →

Pros

  • Very natural, expressive speech (Eleven v3) in 70+ languages
  • Commercial licence from the $6 Starter plan
  • Voice, dubbing, SFX and music under one credit balance
  • Strong API, SDKs and official MCP server
  • Consent checks on voice cloning (voice captcha for Professional clones)

Cons

  • Credits are shared across features and burn fast on long audio or music
  • Free plan is personal use only
  • Music can't be used in film, TV or studio games without an Enterprise licence
  • Professional cloning limited to your own voice

Pricing: Free plan, paid from $6/mo  ·  text-to-speech voice-cloning dubbing ai-music api

🔥 Deal: 50% off the first month of the Creator plan; annual billing gives 2 months free

2

Descript Freemium

Edit video and podcasts by editing the transcript, with an AI co-editor

8.6/10

What it is Descript is a desktop and browser editor from Descript, Inc. that turns your recording into a transcript you can edit like a document: delete a sentence in the text and the matching audio and video are cut. It is used for podcasts, talking-head YouTube videos, webinars and the short clips cut from them. Its AI co-editor, Underlord,… Read more →

Pros

  • Edit video by editing the transcript
  • Studio Sound and Eye Contact fix common recording problems
  • Wide model choice: Veo 3.1, Kling, Seedance, Nano Banana, GPT Image
  • API and MCP integration included for paying users
  • Dubbing into 30 languages

Cons

  • Free plan is 720p with a watermark and only 1 media hour
  • Media hours and AI credits cap heavy users
  • Less precise than a pro NLE for complex timelines
  • Per-seat pricing adds up for teams

Pricing: Free plan, paid from $24/mo  ·  text-based-editing podcast transcription ai-dubbing video-editor

3

Riverside Freemium

Remote podcast and video recording studio with AI editing, clips and translation

8.6/10

What it is Riverside is a browser and mobile studio for recording podcasts and video interviews remotely. It records each guest locally, so audio and video stay high quality even on a poor connection, then uploads separate tracks. A transcript-based editor and AI tools turn recordings into finished episodes, clips and promo assets. Key features - Separate local recordings per… Read more →

Pros

  • Local multitrack recording up to 4K/48 kHz
  • Transcript editing plus Magic Clips and AI Co-Creator
  • Translation and dubbing into 30+ languages
  • Mobile and Mac apps

Cons

  • Free plan has a 720p watermark and only 2 one-time hours of multitrack
  • Recording and download hours are capped per month
  • Livestreaming and multiple studios require Grow ($39)
  • AI models aren't disclosed

Pricing: Free plan, paid from $29/mo  ·  podcast-recording remote-interviews video-podcast clips

🔥 Deal: Annual plans save up to 20% (Pro $24/month instead of $29)

4

Gemini Notebook (formerly NotebookLM) Freemium

Google's source-grounded notebook that turns documents into audio and video overviews

8.4/10

What it is Gemini Notebook is Google's research notebook, called NotebookLM until Google renamed it on 16 July 2026. You upload sources (PDFs, docs, sites, videos) and it answers questions with citations to those sources, then turns them into Audio Overviews (podcast-style conversations), Video Overviews, slide decks, infographics, reports, flashcards and mind maps. The old notebooklm.google.com address redirects to notebook.google.com.… Read more →

Pros

  • Answers stay grounded in the sources you upload
  • Generous free plan: 100 notebooks, 50 sources each, 3 audio and 3 video overviews a day
  • Audio Overviews, Video Overviews, slide decks, infographics, mind maps and reports
  • Syncs with the Gemini app; code execution on higher tiers

Cons

  • Output styles are fixed and hard to brand or edit
  • Cinematic video overviews and the highest limits need AI Pro or Ultra
  • Renamed in July 2026, and plan limits changed again in September
  • Only as good as the sources you feed it

Pricing: Free plan, paid from $4.99/mo  ·  research google audio-overviews study summaries

5

Auphonic Freemium

Automatic audio post-production: levelling, noise reduction, loudness and transcripts

8.2/10

What it is Auphonic is an Austrian web service and API that automatically post-produces spoken-word audio and video. You upload a recording, or connect a watch folder or a hosting service. Auphonic levels the voices, removes noise and reverb, cuts filler words and silence, hits a loudness target and publishes the file with metadata and chapters. Key features - Intelligent… Read more →

Pros

  • Reliable automatic levelling and loudness
  • API and CLI on every plan, including free
  • One-time credits that never expire
  • Transcripts, chapters and publishing automation

Cons

  • Free productions carry an Auphonic jingle
  • Transcription and show notes are paid only
  • No recording or creative editing
  • USD prices are shown only in the browser (about $13 for S)

Pricing: Free plan, paid from $13/mo  ·  audio-post-production loudness podcasting api

🔥 Deal: Yearly billing saves 20% on recurring credits

6

Adobe Podcast Freemium

Browser tools from Adobe that make voice recordings sound studio-quality

7.8/10

What it is Adobe Podcast is Adobe's set of web-based audio tools for speech. It's best known for Enhance Speech, which removes noise and echo from voice recordings and makes them sound as if they were made in a studio. It also includes a Mic Check tool and a browser studio for recording and editing by transcript. Key features -… Read more →

Pros

  • Fast, very effective noise and echo removal
  • Generous free tier (about 1 hour/day)
  • Runs in the browser
  • May be included with Creative Cloud or Express Premium

Cons

  • Strong settings can sound over-processed or robotic
  • Not a full editing or publishing suite
  • Daily processing caps even on Premium
  • Pricing couldn't be read on Adobe's own page

Pricing: Free plan, paid from $9.99/mo  ·  audio-cleanup speech-enhancement podcasting adobe

7

Castmagic Paid

Turn podcasts and calls into show notes, posts, clips and a searchable media library

7.7/10

What it is Castmagic is an AI content tool from Castmagic, Inc. that transcribes audio and video (podcasts, interviews, Zoom calls, webinars) and turns each recording into written and visual assets: show notes, titles, blog posts, newsletters, social posts, quotes, captioned vertical clips and image carousels. It also acts as a searchable library of everything you have recorded. Key features… Read more →

Pros

  • Turns one recording into dozens of written assets
  • Unlimited AI generation; you only pay for transcription hours
  • Claude connector (MCP) and REST API
  • Clips, audiograms and carousels included

Cons

  • No permanent free plan
  • Drafts need editing to match your voice
  • Clipping less advanced than dedicated clip tools
  • Monthly billing about 30% more than the advertised annual price

Pricing: Paid from $19/mo  ·  podcast repurposing show-notes transcription content-library

8

TurboScribe Freemium

Unlimited AI transcription for a flat fee, with a free daily allowance

7.6/10

What it is TurboScribe is a web-based AI transcription service that sells unlimited transcription for one flat subscription. You upload audio or video files, it transcribes them with speaker labels and timestamps, and you can export transcripts and subtitle files or translate them. It became popular with podcasters, students, journalists and YouTubers because its free tier is usable for small… Read more →

Pros

  • Usable free tier: 3 files a day up to 30 minutes
  • Flat-rate unlimited transcription
  • Handles files up to 10 hours and bulk uploads
  • Translation into 134+ languages

Cons

  • AI only, no human proofreading
  • Basic editor compared with Descript or Happy Scribe
  • Fair-use limits apply to 'unlimited'
  • Pricing could not be verified on the vendor page

Pricing: Freemium  ·  transcription unlimited subtitles free-tier whisper

9

Happy Scribe Freemium

AI and human transcription, subtitles and translation in 150+ languages

7.8/10

What it is Happy Scribe is a Barcelona-based transcription and subtitling platform. It offers AI transcription and subtitles, an online subtitle editor, translation and human-proofread services in one place, and is used by media companies, universities, researchers and video teams. Key features - AI transcription and subtitles in 150+ languages - Subtitle editor with styling, timing and burn-in, plus exports… Read more →

Pros

  • 150+ languages for AI transcription and subtitles
  • Human proofreading available from $2/min
  • Good subtitle editor and export formats
  • Annual Basic plan is $8.50/month

Cons

  • Free plan is only a 10-minute AI trial
  • Only 120 AI minutes on Basic
  • Unused plan minutes do not roll over
  • No AI voice dubbing

Pricing: Free plan, paid from $17/mo  ·  transcription subtitles translation human-proofreading captions

10

Rev Freemium

AI and human-verified transcription, captions and subtitles, now focused on legal work

7.4/10

What it is Rev is a US transcription company that combines AI transcription with a network of human transcribers. It has repositioned its platform around investigative and legal work (case files, depositions, evidence review), but still sells human-verified transcripts, captions and foreign subtitles to video and podcast creators. Key features - AI transcription with per-user minute allowances - Human transcription… Read more →

Pros

  • Human-verified transcripts and captions at 99%+ accuracy
  • Clear per-minute human pricing from $1.99/min
  • Large AI minute allowances on paid plans
  • Legal-formatted transcript options

Cons

  • Platform now focused on legal and investigative users
  • Essentials covers only English or English and Spanish
  • Foreign subtitles cost $6.49-$15.99/min
  • Per-seat subscription pricing

Pricing: Free plan, paid from $29.99/mo  ·  transcription captions human-transcription subtitles legal

AI models behind it

Model map →

The same model is often sold by several apps at different prices.

Eleven v3 🧠 ModelFreemium

ElevenLabs' expressive text-to-speech model with audio tags and 70+ languages

ElevenLabs · 2026-02

8.8 Visit ↗

Whisper large-v3-turbo 🧠 ModelOpen source

OpenAI's open-source speech recognition for transcripts and subtitles in 99 languages

OpenAI · 2024-10 · open weights

Gemini 3.8 Flash TTS 🧠 ModelPaid

Google's prompt-directed TTS with 2,000+ voices, 100+ languages and consented cloning

Google DeepMind · 2026-09

8.0 Visit ↗

Chatterbox Multilingual V3 🧠 ModelOpen source

Resemble AI's MIT-licensed TTS with zero-shot voice cloning and built-in watermarking

Resemble AI · 2026-06 · open weights

7.6 Visit ↗

Sonic-3.6 🧠 ModelFreemium

Cartesia's low-latency TTS for voice agents and narration, 44 languages

Cartesia · 2026-08

7.6 Visit ↗

Kokoro-82M v1.0 🧠 ModelOpen source

Tiny Apache-licensed TTS model with 54 voices in 8 languages that runs anywhere

hexgrad · 2025-01 · open weights

7.4 Visit ↗

GPT-4o mini TTS 🧠 ModelPaid

OpenAI's steerable text-to-speech API with 13 voices and prompt-based style control

OpenAI · 2025-12

7.4 Visit ↗

Workflows and automations

All workflows →

Open Notebook 🧩 WorkflowOpen source

Self-hosted NotebookLM alternative for research notes and multi-speaker podcasts

★ 39k

7.9 Visit ↗

WhisperX 🧩 WorkflowOpen source

Fast Whisper transcription with word-level timestamps and speaker diarization

★ 24k

ElevenLabs Skills 🧩 WorkflowOpen source

Official skills for text-to-speech, dubbing, music and sound effects via ElevenLabs

★ 460

Podcastfy 🧩 WorkflowOpen source

Python package that turns web pages, PDFs and videos into AI podcast conversations

★ 6.6k

Before you publish on Podcasts (Spotify, Apple)

Spotify

Spotify bans unauthorised AI voice clones and impersonation, filters spam uploads, and shows AI credits (DDEX standard) that artists submit through distributors.

What must be labelled
There is no general duty to label AI music. Vocal impersonation of a real artist is allowed only with that artist's permission. AI-use credits (vocals, instrumentation, post-production) are voluntary.
How to disclose
Submit AI disclosures through your label or distributor using the DDEX AI-credits standard. Spotify shows them in the song credits.

All platforms · Official policy ↗

Apple Podcasts

Apple Podcasts content guidelines (sections 1.11 and 1.12) require prominent disclosure of AI-generated audio or video and ban misleading uses of AI.

What must be labelled
Audio or video generated with AI, including synthetic voices, AI hosts or on-screen personas, and AI replicas of real people. Using AI to fabricate news or manipulate clips into false narratives is banned.
How to disclose
Disclose prominently in the content itself and in the metadata (description/notes) of every episode and the show.

All platforms · Official policy ↗

Same format, other platforms

–

More for Podcasts (Spotify, Apple)

Every tool for podcasts Commercial use & watermarks

Popular searches