Corti AssistantDelivered as a modular API,
/streams provides a stateful interaction framework for developers to embed clinical-grade intelligence directly into their healthcare applications, creating safer, leaner, and more trusted AI experiences at the point of care.Using the API
Initiate a
/streams by creating an Interaction, which will return a web socket URL along with the interactionId.Connect to the web socket and set your configuration:
| Parameter | Description |
|---|---|
primaryLanguage | Spoken language to be transcribed |
diarize | Enable speaker separation (most useful on single channel audio) Note the legacy parameter isDiarization is still accepted |
isMultichannel | Enable multichannel audio. |
participants | Assign speaker roles for audio channels. Must be used in conjunction with multichannel: true. |
mode.type | Define facts or transcription depending on the desired real-time output |
mode.outputLocale | Output language for extracted facts (required with "type":"facts") |
See detailed configuration options here
Receive transcripts every ~3 seconds and facts every ~60 seconds (standard response times can adapted for custom response times).
Features
Languages
Corti speech to text is specifically designed for use in the healthcare domain. A tier system has been introduced to categorize functionality and performance that is available per language and endpoint. Languages in the Enhanced and Premier tiers have the utmost functionality and recognition accuracy - they’re the ones recommended for dictation use.
Audio Configuration
With support for mono or multi-channel audio, with live transcoding and a variety of file formats to choose from, don’t let the complexities fo audio capture and processing inhibit opportunities for real-time intelligence. Read more about our recommendations and best practices.
FactsR
FactsR™ is a real-time agentic reasoning system for clinical consultations. Designed with ambient documentation in mind, FactsR reduces general purpose AI driven “note bloat” by 65 percent, keeping records precise, relevant, and tightly aligned with the actual clinical conversation.
Formatting
Speech to text can be used to create a verbatim transcript of the audio; however, some content is not documented in the same manner as it is verbalized. The
Server defaults are applied and configuration of formatting preferences is not currently exposed through this endpoint as with
formatting features assures that key information (dates, numbers, measurements, etc.) are output as expected in the transcript. Server defaults are applied and configuration of formatting preferences is not currently exposed through this endpoint as with
/transcribe.Diarization
Diarization is the process of segmenting an audio recording by speaker, assigning portions of speech to distinct identities (e.g., “Doctor,” “Patient”). This enables accurate transcription, attribution, and analysis of multi-speaker clinical conversations, but is not required for effective AI scribing or workflow speech-enablement.
Audio Events
Real-time events during audio streaming about quality and speech activity, intended to notify integrator of audio health degradation, periods of silence, or other events that could support application behavior or user warnings.
Replacements
coming soonAbility to define words or phrases that should be returned in place of the standard output by the speech-to-text model.
Keyterms
Bias speech-to-text output so that new words can be introduced to the system vocabulary (e.g., surnames) or to improve recognition reliability for homophones and words with ambiguous pronunciation.
Please contact us for more information or help.