In-person interviews give you an opportunity to connect on a deep level with customers. But analysis of your conversation can be slow without a transcript to reference later on. If you record audio of the interview, you can move quickly to actionable findings without delay by using AI to automatically transcribe everything. AI interview transcription in Aha! Discovery converts uploaded video or audio into accurate, time‑stamped text in minutes.
Click any of the following links to skip ahead:
Overview
The AI assistant transcribes an uploaded video or audio file into time-stamped text directly in an interview record. Choose from over 100 languages and the number of speakers in your recording, and the AI assistant will transcribe your file, automatically distinguishing speakers. When transcription is complete, you can use the AI assistant to analyze the interview or manually capture highlights in the transcript just like you can with an uploaded VTT file.
AI transcription consumes AI credits. The number of credits used depends on the interview's length. For example, using AI to transcribe a 60-minute video requires around 14 credits.
Transcribe a video or audio recording
Contributors can upload and transcribe video and audio interviews with a few simple steps:
Open the interview record.
Click Upload video or audio. Select an MP4 video or MP3 audio file from your computer to upload.
After the file uploads, click Transcribe.
Select the Language spoken in the video or audio file and enter the number of speakers. Then, click Start transcription.
When the transcription loads in the interview record, it is ready for analysis.
Re-transcribe video or audio
You can ask the AI assistant to re-transcribe video or audio if necessary. Any highlights or AI analysis you captured in the previous transcript will be lost.
Re-transcription consumes AI credits.