Skip to main content
Follow along with the runnable example. This guide walks through the File transcription example in corti-examples — bootstrap your build from it or use it as reference.
Not all dictation is real-time. When you have a pre-recorded file — an uploaded recording, or one you archived from a live session — use the /transcripts endpoint to generate a transcript offline. Unlike the streaming /transcribe path, this is a REST, synchronous-to-asynchronous workflow: you submit a recording and poll for the finished transcript.

​
The pipeline

1

Create or select an interaction

An interaction is the container that groups recordings and transcripts.
2

Upload the audio

Upload a new file, or reuse a recording already attached to the interaction.
3

Create the transcript (async)

Submit the recording with async: true to get a transcript id back immediately.
4

Poll, then fetch

Poll the transcript status until completed, then fetch the finalized transcript.

​
Generate the transcript

The pipeline follows the four steps above. See the file transcription example in corti-examples for the full SDK implementation.
For the endpoint details — the sync-to-async timeout, status codes, size/duration limits, and the full request/response schema — see the Recordings and Transcripts reference and the Create Transcript API spec.

​
Transcription parameters

/transcripts serves both dictation and conversational audio. Set the parameters to match your source:
For single-speaker dictation recordings, isDictation: true is the closest offline analog to the real-time /transcribe dictation path. For multi-speaker conversations, see Diarization.

​
Next steps

Recordings and Transcripts

The /transcripts endpoint reference: workflow, limits, and features.

Audio Archive

Capture and store the live dictation audio you can later transcribe here.

Example code

The complete, runnable File transcription example in corti-examples.
Please contact us for help or questions.