Skip to content

Project Settings

Every project carries settings that apply to all of its uploads. Some are fixed when the project is created; others can be changed at any time.

To see them, open your project and click Configuration. The dialog is titled Project Settings, and its first note explains the split: “Transcription settings cannot be changed after a project is created.”


These appear greyed out in the dialog. They are shown so you can check what a project was created with.

Chosen in the New Project wizard, and the one setting worth thinking about before you click Create:

Audio TypeBest ForHow It Helps
InterviewsOne-on-one conversationsOptimized for 2 speakers, clear turn-taking
Focus GroupsGroup discussionsBetter handles multiple speakers, overlapping speech
Call Center CallsPhone/video callsHandles varying audio quality, echo

Call Center Calls is also what unlocks the call-center features: COPC Evaluation, Calls Analysis, call metadata, automatic on-arrival analysis and the Call Center Report. It cannot be changed later — a project created with the wrong type has to be recreated.

Language is set to Auto (automatic detection) at creation, which handles mixed-language content, and is not user-configurable.

Word-level timestamps are always enabled at creation and are not user-configurable. They are what makes it possible to jump from a quote in an analysis result to the exact moment in the transcript.


The rest of the dialog can be edited whenever you like. Click Save to apply.

Recordings are erased permanently this many days after upload. Transcripts and analysis results are kept, so past work stays readable after the audio is gone.

Leave the field empty to follow your team’s retention policy instead of setting a per-project one.

Transcribe recordings on private infrastructure only

Section titled “Transcribe recordings on private infrastructure only”

Recordings are processed by a speech recognition service operated by Uspeech and are never sent to a third-party provider.

  • Transcription may take longer
  • A recording that cannot be processed privately fails rather than being sent outside
  • Your team can require this for every project, in which case the checkbox is switched on and locked, with a note explaining why

Applies to new transcriptions only — recordings already transcribed are unaffected.

Shown underneath the private-transcription setting. It tells the recognizer how many people are on the recording instead of leaving it to work that out.

OptionWhen to use it
Detect automaticallyThe number varies between recordings — interviews with a second participant, focus groups, calls that get transferred
1–10 speakersEvery recording in the project has the same number of voices

Stating the count exactly is both faster and more reliable: left to itself, the recognizer can split one voice across two speakers. Call projects default to 2 speakers for that reason; other project types detect automatically unless you say otherwise.

Applies to new transcriptions only.

Call Center Calls projects also carry Analyze calls automatically as they arrive, with the analysis types, rubric and batch sizing behind it. See Automatic Analysis.