Product updates

Changelog

Major improvements, new voices, and feature launches - curated for our users.

New Feature

Talking video option on Famous Voice pages

On Famous Voice generator pages you can choose Audio or Video before you generate. Video keeps the same continuous loading experience, then animates a portrait so the famous voice looks like it is speaking your script.

New Feature

Adjust tracks in Music Studio

After you generate a song, paid plans can Adjust it instead of starting over. Change vocals, vibe, genre, lyrics, instruments, or make it instrumental, and get two new versions. Same credit cost as a fresh generate.

New Feature

Talking Photo - make any face photo speak

Upload a clear face photo, type a short script, pick a voice, and get a lip-synced talking video. Guests and free accounts get one watermarked video per month (up to about 20 seconds of speech). Paid plans remove the watermark, allow longer clips, and bill from your character credits by the second. Finished videos save to your library, and recent ones show on the tool page.

New Feature

AI Music Studio - original songs from a prompt or your lyrics

Music Studio is live. Describe a vibe or paste your own lyrics and get two full takes - vocals or instrumental - to compare, with genre, language, and length controls. Guests and free accounts get one free generate to try it; paid plans create more for 2,000 credits per generate. Finished tracks save straight to your library.

Improvement

Indonesian voice cloning works reliably again

Creating a voice clone with Indonesian selected now processes your recordings and uploads correctly, the same way English already did.

Improvement

Large PDFs keep their full text for speech

Long or complex PDFs no longer lose pages or sections during extraction, so more of your document makes it into the audio.

Improvement

Faster long text-to-speech and clearer numbers

Long scripts generate more quickly, and numbers in non-English text are spoken with more natural pronunciation.

Improvement

Faster PDF-to-speech checkout

Paid PDF conversions start sooner by finishing heavy document processing after payment instead of blocking the checkout step.

New Feature

Full Filipino language support across the site

You can use AnyToSpeech in Filipino (/fil) across tools, navigation, and SEO pages — not just a partial translation.

New Voices

New Filipino voices in the voice library

New Filipino voices with preview samples are available in the voice picker for text-to-speech and related tools.

Design

Clearer homepage hero and trust highlights

The logged-out homepage got a cleaner hero, stronger sign-in calls to action, and trust highlights that stay readable on mobile.

Improvement

More accurate How Old Do I Sound? results

The age estimator is more stable across age ranges and now explains the main factors behind your result.

New Feature

Famous voices in the mobile app voice catalog

The mobile app voice catalog now includes famous voices and richer accent details in the picker.

New Feature

Optional progressive PDF upload and page saves to your library

You can opt into progressive PDF upload for large files, and converted pages can be saved to your audio library.

Improvement

Famous and character voices on paid plans for main TTS tools

On the main text-to-speech tools, famous and character voices are available on paid plans so free usage stays focused on the standard voice library.