Please review the languages page to learn more about languages supported per endpoint, functionality per language tier, and language code to use in API requests.Please review the dictation overview page to learn more about features beyond speech-to-text.
Corti Speech Recognition Endpoints
Transcribe
Real-time speech-to-text and command-and-controlPower dictation workflows and speech-enable your application
Stream
Real-time conversational clinical intelligencePower ambient documentation or decision support workflows
Transcripts
Speech-to-text via batch audio file processingEnable dictation or conversational transcription
Endpoint Functionality
| Connection | WSS | WSS | REST |
| Data processing | Synchronous | Synchronous | Asynchronous 1 |
| Architecture | Stateless | Stateful | Stateful |
| Speech-to-text | Dictation | Conversational transcript | Dictation or transcript |
| Diarization | |||
| Multichannel | |||
| Custom command definition | |||
| Automatic punctuation | |||
| Spoken punctuation | |||
| Formatting | beta | coming soon | coming soon |
| Vocabulary | coming soon | coming soon | coming soon |
1 Speech recognition accuracy for async audio file processing via
/transcripts endpoint may be degraded as compared to real-time recognition via the /transcribe and /stream endpoints. See the languages page or release notes for more information.Speech Recognition Performance Tiers
Corti speech recognition uses a tier system to categorize functionality and performance that is available per language:| Tier | Description | |
|---|---|---|
| Base | AI-powered speech-to-text capability, ready to integrate with healthcare IT solutions via the /stream or /transcripts API | Up to 1,000 |
| Enhanced | Base plus optimized medical vocabulary for a variety of specialties and support for real-time dictation via the /transcribe API | 1,000-99,999 |
| Premier | Enhanced plus speech recognition models delivering the best performance in terms of accuracy, quality, and latency | 100,000+ |
Learn more about how languages are supported here.
Please contact us if you are interested in features that are not listed here, need help determining the best speech recognition endpoint for your needs, or have questions about how to configure your API requests.