NIN-ClearSpeech-v1
Bring the voice forward.
Discuss this model ↗Upcoming model. Capabilities describe our plans; weights and inference are not available.
Bring the voice forward.
Reduce background noise in voice recordings before dictation and transcription for NINK and NINXL.
Reduce background noise in voice recordings.
Prepare clearer audio for dictation and transcription workflows.
Evaluate how enhancement affects speech intelligibility and downstream transcripts.
See the intended workflow.
Illustrative example, authored by NIN. This is not a live model prediction.
Recording scenario
A voice note recorded with a fan running in the background.
Intended audio treatment
Reduce the fan noise while preserving the speaker’s voice for transcription.
This is a described audio scenario, not a playable processed sample. Enhancement can alter speech and needs evaluation.
On-device / private-hosted
Built around your workflow.
On-device execution in NIN products and private hosting for organisational workflows are intended deployment options.
Details after evaluation.
Model size, hardware requirements, supported formats, licensing and measured performance will be documented when available. No release date is announced.
Where could NIN-ClearSpeech-v1 help?
Tell us about your workflow, the data it uses and what a useful result would look like. Discuss an evaluation partnership with NIN.
Discuss this model ↗