What it does

ZenMic generates spoken audio from written material. You can paste a URL, a document or just a topic idea, or bring your own script and paste it or write it line by line. The site says you review and can edit the script before any audio is made. Episodes can have up to six speakers, each with their own voice, and the site says it covers more than 100 languages. You can record 10 to 30 seconds to clone your own voice, describe a voice in words to have one created, and direct emotion on each line, such as whispers, laughs and sighs. Templates cover things like a founder pitch debate, an ESL dialogue, a short report summary and a tech news brief. Finished audio can be downloaded as MP3, embedded with a web player, or published through an RSS feed to Spotify and Apple Podcasts. The site also mentions a REST API, a way to turn audio into captioned videos, and a set of small free tools such as a podcast name generator. The site says you can start for free without a credit card. Plan details sit on a separate pricing page that was not part of the text read here.

Capabilities

Turns URLs, documents, topics or your own script into multi-speaker audio
Line-by-line script editing before any audio is generated
Up to six speakers, with voice cloning and voices described in words
More than 100 languages and per-line emotion direction
MP3 download, embeddable player and RSS feeds for podcast apps
REST API and captioned video output

When to use it

You want to make a podcast episode from an article, document or idea without recording
You teach languages or run training and need spoken dialogue in many languages
You want to host a show with a cloned version of your own voice