A show that can be re-cut after it is recorded.
Streaming
audio starts before the render finishes, gap-free at any length
The host voice is a request parameter, cloned from ten seconds, so an intro or an ad read comes back as a finished WAV ready for the timeline. Most podcast audio is not the conversation, it is the parts you rewrite after recording.
The parts that change after recording
An ad read swaps when the sponsor does. A correction lands the week after publication. Each is a re-render of existing episodes, priced by length on a meter and priced at nothing here.
audio
a host segment, mid-episode
generated 2026-08-05
English
“So here is the part that genuinely surprised me, and I want to be careful about how I say it, because I got it wrong for about two years. Everyone assumed the cost was the problem. Every conversation started there, every proposal led with it. It was not the problem. The cost was a symptom of something further upstream, and once you see the thing upstream, you cannot unsee it in any of these companies.”
Leo · 21.1 s · podcast · synthetic host
What the API does here
- One request returns one complete WAV, an ad read or an intro, ready to drop into the edit.
- The host voice is a request parameter, cloned from ten seconds of the real host with no enrolment step.
- Emotion and prosody per request, so a correction reads as a correction and a cold open reads as a cold open.
Notes
Can we clone the host so inserts match the show?
Yes. Ten seconds of the host speaking is enough. Cloning requires a consenting speaker, and every clip carries an inaudible watermark.
Is this good enough to replace a human read?
That is your judgement to make on your own script, which is why the console on the home page runs the production API on whatever you type.
A key and one stream to build this on, the same production API this page measures.
Get a key for this use case