Cue
Cue aligns existing text with audio. It also supplies timing within the Scribe pipeline and is available separately through the Forced Alignment API.
Alignment and recognition
The research team built Cue as a smaller successor to its earlier aligner. It can process long recordings without first splitting them into short chunks. The October 2026 article describes a model already deployed; it does not establish the first release date.ElevenLabs: Cue alignment research
The standalone API does not support diarized transcript input. Its capability page lists 29 languages, while the newer research article describes broader model coverage. These are different documented scopes.ElevenLabs Forced Alignment API capabilitiesElevenLabs: Cue alignment research
Practical guidance. Use recognition to create an unknown transcript. Use forced alignment when the text is already known and accurate timing is the missing information.ElevenLabs Forced Alignment API capabilities
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | API |
| Input | Audio plus a supplied transcriptElevenLabs Forced Alignment API capabilities |
| API limits | 10 hours, 3 GB and 675,000 text charactersElevenLabs Forced Alignment API capabilities |
Related models
- Scribe v2
ElevenLabs · Scribe
Batch speech-recognition model for long recordings, structured transcripts and multilingual audio.
Launch date API · Provider product - Scribe v2 Realtime
ElevenLabs · Scribe
Streaming recognition model with partial and committed transcripts.
Launch date API · Provider product