Text to Speech for Podcasts
Paste a script, pick a voice, and get an MP3 back. Useful for solo narration, daily briefings, and — with the multi-speaker studio — scripted interviews or dialogue where each speaker needs a different voice.
No login • 580+ voices in 75+ languages • Up to 5,000 characters per generation
What this is actually good for
If your show is a script you read out loud — a daily news briefing, a solo explainer, a research summary — the single-narrator studio handles it directly: paste the script, choose a voice and pacing, generate, download the MP3, drop it into your editor.
If the format has more than one voice — a scripted "interview," a two-host cold open, a dramatized segment — use the multi-speaker studio instead. You write the script as labeled lines, assign a different AI voice to each speaker, and it renders as one combined audio file rather than several clips you have to stitch together yourself.
What this isn't good for: unscripted, conversational banter. AI narration reads what you write — it doesn't riff. If your show's appeal is two people reacting to each other in the moment, that still has to be recorded live.
Controlling pacing with pause tokens
Podcast narration lives and dies on pacing — a script read at one flat speed sounds robotic
fast. The editor supports three pause lengths you can drop directly into your text:
[[p400]] for a short beat,
[[p700]] for a sentence break,
and [[p1200]] for a segment transition.
Example: "Today's top story — a shift in interest rates. [[p700]] Here's what it means for you. [[p400]] First," — the two pauses do the work a human host would do naturally with breath and emphasis.
Which mode fits your format
Single voice
- Daily news or market briefings read from a script
- Solo explainer or commentary episodes
- Research summaries and monologue-style shows
Multi-speaker
- Scripted "interview" segments written as Q&A
- Two-host cold opens or scripted banter
- Dramatized or character-driven fiction podcasts
From script to MP3
1. Paste or import the script
Type directly, or import a PDF/Word doc. One generation covers up to 5,000 characters — longer episodes get split into a couple of sections.
2. Pick voice and pacing
Choose a narrator from 580+ voices, adjust pitch/rate/volume, add pause tokens where you want a beat.
3. Generate and download
Preview the MP3 in the browser, then download it straight into your editing timeline.
One honest note
Listeners can usually tell a script is AI-narrated within the first few sentences, especially on longer-form shows. That's not a dealbreaker for briefings, summaries, or explainer content where the value is the information — but if your show's whole appeal is a distinct human voice or unscripted chemistry between hosts, text to speech won't replace that, and pretending otherwise to your audience is a bad idea.
Frequently asked questions
Can I use this for a two-host podcast?
For a scripted version, yes — write it as labeled lines and use the multi-speaker studio to assign a different voice to each host. For live, unscripted back-and-forth, no — that still needs to be recorded.
How long can one episode be?
Each generation covers up to 5,000 characters (roughly 800–1,000 words, depending on sentence length). For a full episode, generate in sections and combine the MP3s in your editor.
What file do I get?
An MP3, ready to drop into whatever you edit and publish with.
Do I need an account?
No. Open the tool, paste your script, generate.
