Transcription
Use transcription to convert spoken audio into text directly in a conversation. You can record in real time using your device’s microphone, capture computer audio alongside it, or upload a file recorded on a separate device.
How to transcribe audio
Section titled “How to transcribe audio”Record directly in Intric
Section titled “Record directly in Intric”Click the microphone icon in the conversation input to start a live recording. Intric captures audio from your device’s microphone.
To also capture what is playing through your computer’s speakers, enable Include computer audio before you start. This is useful for recording video calls or media playing on your screen.
Click the stop button to end the recording. Intric then sends the audio for transcription.
Upload a pre-recorded file
Section titled “Upload a pre-recorded file”To transcribe a recording made on a separate device, click the attachment icon in the conversation input and select your audio file. Intric transcribes it the same way as a live recording.
Supported file formats depend on the transcription model configured on the assistant.
Which model is used
Section titled “Which model is used”Transcription uses the transcription model configured on the assistant you are using. The same model handles both speech-to-text conversion and speaker detection. Audio data stays within that model’s data handling boundary.
Transcript output
Section titled “Transcript output”Once transcription is complete, the full text appears in the conversation. You can read it, copy from it, and ask the assistant follow-up questions based on the content. For example, ask it to summarise the discussion, extract action points, or translate it into another language.
Speaker detection
Section titled “Speaker detection”When a recording contains more than one voice, Intric segments the transcript by speaker. Each segment gets a generic label: Speaker 1, Speaker 2, and so on, assigned in the order each voice is first heard.
A typical result looks like this:
Speaker 1 Good morning. Could you walk me through the main findings from last week’s report?
Speaker 2 Of course. The data shows a 12 percent increase in response times during peak hours. We think it is linked to the infrastructure change made on Thursday.
Speaker 1 That aligns with what the on-call team reported. What are the next steps?
Note: There is currently no way to assign custom names to detected speakers. That capability is on the roadmap.
Availability
Section titled “Availability”| Deployment type | Status |
|---|---|
| Multi-tenant (cloud) | Available now |
| Dedicated instances | Rolling out within approximately two weeks |
| On-prem | Requires specific configuration. Contact support@intric.ai for help. |