How does text to speech work in DIY AI Studio?

Turn written text into an MP3 recording using an available voice and speaking speed. Review the credit quote before generating, then listen to and download the completed recording.

The text limit is 4,000 UTF-8 bytes; some languages reach it with fewer characters. Available voices depend on the catalogue and your account. Voice-language labels do not guarantee an accent or output language.

Using this tool

Write the words that should be spoken, rather than scene instructions. Spell out abbreviations and ambiguous numbers, and use punctuation for pauses. Check names, dates and specialist terms by listening to the result.

Results are private to your account. Unsaved results expire after seven days; use Save to protect a result from automatic cleanup. You can delete results at any time.

Voice references remain available for 30 days, or longer while their recording is saved. You can delete saved voices at any time.

Generation requires a signed-in account, an active Studio plan and enough credits. Available models and settings can change; review the current credit quote before submitting.

DIY AI Studio is DIY AI’s workspace at diyai.io for creating images, videos, music and voice with one membership and a shared credit balance.

DIY AI Studio and Google AI Studio are separate services.

Eligible customers can try Studio free for 7 days with 50 Studio credits. US$0.00 due today. Then US$9.99/month with 100 credits until cancelled. Card required.

Trial, eligibility and cancellation

A card and email verification are required. Newsletter signup is optional. Credit costs vary by model and settings; check the quote before generating.

One trial per customer and card. Eligibility is checked at signup; eligible existing Free accounts can also apply. This is a limited trial, not an ongoing free plan.

Cancel online before renewal to avoid the monthly charge. Cancelling during the trial ends access and revokes unused trial credits immediately.

Text to Speech

Skip to workspace

Give your words a voice.

AI Text to Speech

Fish Audio / ElevenLabs

Text to Speech

Reference language does not guarantee accent or pronunciation.

Write your script in English. Listen before choosing a voice; the sample language is shown when known.

Use a preset or your own saved voice. Disclose synthetic speech where required.

Add your script to see the credit cost.

The cost depends on text length and voice. Saved voices also include their reference text. Checking the price uses no credits.

Sign in to generate speech.

Voice studio — concept artwork
Concept artworkVoice studio

Your creation will appear here.

WORKING IN THE BACKGROUND

Your generations

Keep creating. Your work continues as you move around Studio.