Vizify audio catalog

Choose an audio model by job, not by brand alone.

The catalog separates speech, dialogue, music, and general audio so incompatible parameters never look interchangeable.

All model typesAudio toolsStart creating audio
Choose by job

Compatible starting points

Text to Speech

Give Vizify the exact text, its language, and how it should be read. It routes to a model that exposes Speech mode, passes only the parameters that model supports, and returns one continuous spoken take of your script.

Open tool

AI Dialogue Generator

Give Vizify named speakers, their lines in order, and how the conversation moves. It routes to a model that exposes Dialogue mode, passes only the parameters that model supports, and returns one multi-speaker conversation in a single track.

Open tool

AI Music Generator

Give Vizify genre, mood, instrumentation, tempo, structure and whether you want vocals. It routes to a model that exposes Music mode, passes only the parameters that model supports, and returns one finished cue, vocal or instrumental.

Open tool

AI Sound Effect Generator

Give Vizify the sound event, the space around it, its timing, distance and texture. It routes to a model that exposes General audio mode, passes only the parameters that model supports, and returns one isolated effect with no music or speech under it.

Open tool
18 available policies

Current audio catalog

Audio model

Voxtral Small Transcribe 3

voxtral-small-transcribe-3
MistralVideoAudio inputOutputs: TextMode: Transcription
Model detailsBrowse tools
Audio model

Voxtral Mini Transcribe 3

voxtral-mini-transcribe-3
MistralVideoAudio inputOutputs: TextMode: Transcription
Model detailsBrowse tools