Skip to content
Multilo Docs

Speech (TTS & STT)

Optional text-to-speech and speech-to-text, built to be opt-in and lightweight.

Speech adds text-to-speech and speech-to-text to Multilo. It’s built to be opt-in and lightweight — off until you turn it on, and sharing the machinery already in the app rather than bundling a second runtime.

Enabling Speech

Speech ships as an optional capability that stays inert until you enable it. Turn it on when you want it, and the engine activates without bloating the rest of the app. It’s delivered as a downloadable pack — see first-party packs.

Read documents aloud

Have Multilo read your draft or a source back to you — a fast way to catch awkward phrasing and proofread by ear.

Dictation & transcription

Dictate text and transcribe speech to text. Transcription reuses the same on-device speech machinery the app already uses to transcribe audio and video sources.

On-device by default

Speech recognition runs on-device with an on-demand model, so audio stays local and you only download what you use.

Minimal by design

Speech reuses Multilo’s existing worker instead of adding a separate runtime, keeping the install light and the app responsive.