StepUp Voice

Open voice workflows for dictation, generation, and reusable speech inside StepUp.

StepUp Voice now stores tenant-scoped presets and generation jobs instead of remaining a static shell. Capture speech, clean it for work, and stage reusable TTS-ready jobs inside the workspace.

This is still a local-first foundation slice. The browser speech capture remains client-side, while StepUp now persists presets, generation jobs, and workflow metadata for later provider and model orchestration.

WorkspaceOpen StepUp Music
Capture

Realtime dictation workspace

Status

Unsupported

Mode

clean

Generations

0

Ready

0

This browser does not expose the Web Speech API. Chrome or Edge on a secure origin will work best for this slice.

Voice library

Presets and generation controls

Loading presets...

Draft studio

Transcript, polished copy, and TTS-ready script

Live transcript

Your spoken transcript will appear here.

Polished result
Choose a cleanup mode to generate a polished draft.
Dictionary

Terminology replacements

Generation queue

Speech jobs

Loading generations...

Voice ops

Operator queue for broken, failed, and under-prepared speech jobs

Loading voice ops queue...

Platform direction

How StepUp Voice fits the suite

Open-source ASR and TTS model orchestration

Foundation framing for the broader StepUp voice stack.

Voice-safe prompt templating and glossary controls

Foundation framing for the broader StepUp voice stack.

Workspace routing into Desk, Docs, Projects, and Automate

Foundation framing for the broader StepUp voice stack.

Future voice-clone governance, approvals, and audit trails

Foundation framing for the broader StepUp voice stack.