Here at Corti, we want to make it easy for organizations to capture speech and convert it into accurate, structured transcripts. This can support clinical documentation, call center operations, clinical reporting, and more.
Three of the most common use cases that we see our customers use are:
Live ambient audio capture (capturing conversations as they happen)
Live dictation workflows (a speaker dictating the exact words they need to convert to text)
Asynchronous audio processing (uploading recordings after the fact)
Live Ambient Audio Capture
When to use it
This is best for scenarios where conversations happen naturally in real time and you want transcripts generated automatically — without disrupting the flow.
Examples
In a clinic, Corti passively listens during patient-clinician interactions and generates a transcript for later documentation.
In a call center, supervisors capture ongoing customer calls for training or compliance purposes.
How it works with the API
Stream live audio from the environment directly to Corti.
Corti continuously transcribes speech into text, segmenting speakers when possible.
The transcript can then feed into other workflows like document generation.
📖 Learn more: Ambient RT workflow | About Corti ASR
Live Dictation Workflows
When to use it
Perfect when someone (like a clinician) wants to dictate directly into the system — short, intentional bursts of speech designed to be transcribed quickly and accurately.
Examples
A doctor dictates notes during or right after a consultation instead of typing.
A caseworker dictates structured reports after a field visit.
How it works with the API
Audio is captured from a microphone and sent live to Corti.
Corti is optimized to recognize clear, single-speaker dictation with high accuracy.
The resulting transcript can be returned in real time or stored for later processing.
📖 Learn more: Dictation overview | Transcription workflow
Asynchronous Audio Processing
When to use it
Sometimes audio isn’t available live — you already have recordings (calls, consultations, interviews) and want transcripts later. This is where asynchronous (async) audio processing comes in.
Examples
A hospital uploads recorded consultations from the day and gets transcripts overnight.
A call center processes large batches of customer service calls for analysis.
How it works with the API
Upload an audio file to Corti.
Request transcription asynchronously.
Once complete, the transcript is available for download and use in other workflows.
📖 Learn more: Ambient async workflow | Upload recordings | Create transcript
Why Organizations Choose These Workflows
Efficiency: Reduce time spent on manual note-taking or typing.
Accuracy: Corti’s ASR (Automatic Speech Recognition) is trained for real-world healthcare and support settings.
Flexibility: Choose the right workflow depending on whether audio is live or pre-recorded.
Integration: Transcripts can easily feed into downstream processes like FactsR or document generation.