How long can the script be?

The Script box takes 8 characters minimum and 5,000 maximum, roughly 800 words. The script pass paces at about 145 words a minute, so a full box is around five and a half minutes of audio. Go past 5,000 and the render is refused with a note to split it into separate renders. There is no duration control, so the audio runs as long as the words do.

What if I paste a brief instead of the words?

The script pass works out which one it is holding. A finished read comes back essentially verbatim. A brief gets written into spoken lines against the project's research, strategy, past winners and brand memory, under a rule that every claim, price and URL must already appear in that grounding. A domain that is not in the data is left unsaid rather than guessed. The spoken script is saved with the MP3.

Can I use my own brand voice?

Yes. Project / brand default is the first entry in Voice, and it resolves to the default voice on your org's connected audio account, a cloned voice included. With nothing connected it falls through to the stock library instead. A fresh connect takes effect straight away rather than waiting out the five minute cache. The ten named voices stay there for a specific read.

What am I charged for?

Per character of the script that gets spoken, not per attempt. Stop is checked before the script pass and again right before the audio call, so a stop that lands in time spends nothing. The charge key is built from the voice, the tier and the exact text, so re-running the same read in the same project bills once rather than twice. Turbo and Draft sit at half the per-character rate of Expressive and Versatile.

Why do tags like [warmly] behave differently?

Expressive reads inline square-bracket tags such as [warmly] or [pause] as performance directions. Versatile, Turbo and Draft would say the brackets out loud, so they are stripped before the read along with the spacing they leave behind. Round brackets are spoken literally on every tier, which is why the script pass is told to use ellipses, dashes and CAPS for emphasis instead.

Fresh out of the oven

These tools are new, so the odd thing may still wobble. If something looks wrong, it probably is. Tell us and we will sort it.

Audio tool

AI voice generator

Paste up to 5,000 characters into the Script box and one MP3 comes back in the same run. Text that is already a finished read is spoken close to verbatim. A rough brief gets turned into spoken lines first, written off your project's research and strategy instead of guesswork. Under Script and delivery, Voice offers ten stock reads plus Project / brand default, which uses the brand voice connected to your org. Stability, Similarity and Style exaggeration are rulers from 0 to 1, and the hint on Style exaggeration says to leave it at 0 for marketing reads. Advanced holds Voice tier: Expressive, Versatile, Turbo or Draft. Billing is per character of the script that gets spoken.

What you get

Produces: voiceover, audio
Input: Starts from a written brief. No upload needed.
Price: Free to try. Sign in when you generate.
Category: Audio

How it works

Four steps, start to finish

The tool is open above. This is the short version of what to do with it.

01 / 04
Paste the script
The Script box is the first field, six rows deep, 8 characters minimum and 5,000 maximum, placeholder "Paste or write the exact text to speak." Finished words are read close to verbatim. A brief is rewritten for the ear first: short sentences, one CTA at the end.
02 / 04
Pick the voice
Under Script and delivery, Voice lists ten stock reads with persona hints, Eric for smooth and trustworthy through Jessica for playful and bright. Project / brand default is the first entry and uses the brand voice connected to your org. Voice tier sits under Advanced.
03 / 04
Set the three rulers
Stability starts at 0.5, with the hint reading 0 for expressive and 1 for consistent. Similarity starts at 0.75. Style exaggeration starts at 0 and its hint says to leave it there for marketing reads. All three step in 0.05. Speaker boost is on by default.
04 / 04
Play it and recut
One MP3 lands in the project and the spoken script is stored on the same artifact, so you can check that no brief text got read out. Change the words and run it again. The same text, voice and tier in one project bills once, not twice.

FAQ

Common questions

Short answers to what people ask before they start.

How long can the script be?: The Script box takes 8 characters minimum and 5,000 maximum, roughly 800 words. The script pass paces at about 145 words a minute, so a full box is around five and a half minutes of audio. Go past 5,000 and the render is refused with a note to split it into separate renders. There is no duration control, so the audio runs as long as the words do.
What if I paste a brief instead of the words?: The script pass works out which one it is holding. A finished read comes back essentially verbatim. A brief gets written into spoken lines against the project's research, strategy, past winners and brand memory, under a rule that every claim, price and URL must already appear in that grounding. A domain that is not in the data is left unsaid rather than guessed. The spoken script is saved with the MP3.
Can I use my own brand voice?: Yes. Project / brand default is the first entry in Voice, and it resolves to the default voice on your org's connected audio account, a cloned voice included. With nothing connected it falls through to the stock library instead. A fresh connect takes effect straight away rather than waiting out the five minute cache. The ten named voices stay there for a specific read.
What am I charged for?: Per character of the script that gets spoken, not per attempt. Stop is checked before the script pass and again right before the audio call, so a stop that lands in time spends nothing. The charge key is built from the voice, the tier and the exact text, so re-running the same read in the same project bills once rather than twice. Turbo and Draft sit at half the per-character rate of Expressive and Versatile.
Why do tags like [warmly] behave differently?: Expressive reads inline square-bracket tags such as [warmly] or [pause] as performance directions. Versatile, Turbo and Draft would say the brackets out loud, so they are stripped before the read along with the spacing they leave behind. Round brackets are spoken literally on every tier, which is why the script pass is told to use ellipses, dashes and CAPS for emphasis instead.

Academy course

Video

Write scenes that cut together, keep one look across them, and get sound that matches.

5 lessons · 25 minStart the course →

More tools

Related tools

The rest of the family. Every one is free to try and runs on the same engine.

All 24tools →

Fresh out of the oven

These tools are new, so the odd thing may still wobble. If something looks wrong, it probably is. Tell us and we will sort it.

Fresh out of the oven

These tools are new, so the odd thing may still wobble. If something looks wrong, it probably is. Tell us and we will sort it.

Audio tool

AI voice generator

What you get

Produces: voiceover, audio
Input: Starts from a written brief. No upload needed.
Price: Free to try. Sign in when you generate.
Category: Audio

How it works

Four steps, start to finish

The tool is open above. This is the short version of what to do with it.

01 / 04
Paste the script
The Script box is the first field, six rows deep, 8 characters minimum and 5,000 maximum, placeholder "Paste or write the exact text to speak." Finished words are read close to verbatim. A brief is rewritten for the ear first: short sentences, one CTA at the end.
02 / 04
Pick the voice
Under Script and delivery, Voice lists ten stock reads with persona hints, Eric for smooth and trustworthy through Jessica for playful and bright. Project / brand default is the first entry and uses the brand voice connected to your org. Voice tier sits under Advanced.
03 / 04
Set the three rulers
Stability starts at 0.5, with the hint reading 0 for expressive and 1 for consistent. Similarity starts at 0.75. Style exaggeration starts at 0 and its hint says to leave it there for marketing reads. All three step in 0.05. Speaker boost is on by default.
04 / 04
Play it and recut
One MP3 lands in the project and the spoken script is stored on the same artifact, so you can check that no brief text got read out. Change the words and run it again. The same text, voice and tier in one project bills once, not twice.

FAQ

Common questions

Short answers to what people ask before they start.

How long can the script be?: The Script box takes 8 characters minimum and 5,000 maximum, roughly 800 words. The script pass paces at about 145 words a minute, so a full box is around five and a half minutes of audio. Go past 5,000 and the render is refused with a note to split it into separate renders. There is no duration control, so the audio runs as long as the words do.
What if I paste a brief instead of the words?: The script pass works out which one it is holding. A finished read comes back essentially verbatim. A brief gets written into spoken lines against the project's research, strategy, past winners and brand memory, under a rule that every claim, price and URL must already appear in that grounding. A domain that is not in the data is left unsaid rather than guessed. The spoken script is saved with the MP3.
Can I use my own brand voice?: Yes. Project / brand default is the first entry in Voice, and it resolves to the default voice on your org's connected audio account, a cloned voice included. With nothing connected it falls through to the stock library instead. A fresh connect takes effect straight away rather than waiting out the five minute cache. The ten named voices stay there for a specific read.
What am I charged for?: Per character of the script that gets spoken, not per attempt. Stop is checked before the script pass and again right before the audio call, so a stop that lands in time spends nothing. The charge key is built from the voice, the tier and the exact text, so re-running the same read in the same project bills once rather than twice. Turbo and Draft sit at half the per-character rate of Expressive and Versatile.
Why do tags like [warmly] behave differently?: Expressive reads inline square-bracket tags such as [warmly] or [pause] as performance directions. Versatile, Turbo and Draft would say the brackets out loud, so they are stripped before the read along with the spacing they leave behind. Round brackets are spoken literally on every tier, which is why the script pass is told to use ellipses, dashes and CAPS for emphasis instead.

Academy course

Video

Write scenes that cut together, keep one look across them, and get sound that matches.

5 lessons · 25 minStart the course →

More tools

Related tools

The rest of the family. Every one is free to try and runs on the same engine.

All 24tools →

AI voice generator

Paste the script

Pick the voice

Set the three rulers

Play it and recut

Video

AI voice generator

Paste the script

Pick the voice

Set the three rulers

Play it and recut

Video