Live captions

Tap or click the caption for fullscreen — or use the overlay link below in ProPresenter / OBS.

Translation

Whole sentences — wait until each sentence is finished instead of word-by-word (applies to the screen and the audience readers)

AI patience — how long a pause counts as the end of a sentence. Higher = the AI hears more before it finishes speaking (better translations, no cut-off endings); lower = snappier voice. Applies from the next Start.

No sound detected yet — check that the right microphone is selected, isn't muted, and that the speaker is talking into it.

The AI voice comes from the same translation session — it costs no extra plan hours. Broadcasting uses ~0.5 Mbit/s of upload while on; listeners press Listen on their reader page. With both voice options off, a text-only engine is used (captions stream word by word, no voice is generated).

Caption the same language too

Speech that is already in a chosen language is normally skipped. With this on it is captioned as it is — Swedish speech gives Swedish text when Swedish is a chosen language. Costs the same as translation; with the voice playing here, the microphone pauses while the voice speaks. Applies from the next Start.

Advanced: AI instructions & profanity filter

Profanity filter (per-language blocklist)

Conversation mode Beta

Two people, one device: each person is voice-enrolled, then everything they say appears — and can be spoken — in the other person's language. Opens as its own screen.

Open conversation mode

Usage & overlay

Overlay link — ProPresenter Prop web object / OBS Browser Source: