ElevenLabs Cue

Cue is ElevenLabs’ new forced alignment model. It places every character of a transcript on the audio timeline, handles recordings of any length in a single pass, and is built into every Scribe transcription. ElevenLabs reports 179 ms average timing error on full recordings and about half a second to align an hour of audio. It’s also available on its own through the Forced Alignment API.