What's new at TextToAudio
A running record of the models, voices and workflow improvements shipped to the studio.
v2.4 — Expressive V2
The new Expressive V2 model is now the default for every paid plan. It improves sentence-level pacing, emotional range and pronunciation consistency while keeping the same simple workflow.
- More natural pauses and emphasis.
- Clearer multilingual pronunciation.
- Faster voice switching in the studio.
- Improved long-form export reliability.
v2.3 — Studio controls
Added dedicated volume, speed and pitch controls with one-click reset. Audio format selection now remembers your last export preference.
v2.2 — Voice catalogue
Expanded the catalogue with new narrator, commercial, documentary, character, ASMR and social-first voices. Search and filtering are available in AI Voices.
v2.1 — Projects and history
Projects now keep a complete generation history, including the script, selected voice and output format. Duplicate a previous setup in one click.
v2.0 — A faster studio
Rebuilt the text editor and generation flow for a cleaner, faster experience. The workbench now supports multiline scripts and clearer character counting.
Have a product idea?
Tell us what would make your voice workflow better at support@texttoaudio.lol
Our support team replies within one business day, Monday through Friday.