Skip to main content
Use Transcription for media you already have, such as an interview or a lecture video. Meetings you record live in Recordings, and captioning sessions in Live Captioning. All three share the same recording view but list different sources.

​
Import a file

  1. Choose a model in Settings → Transcription Models.
  2. Open Settings → Transcription, click Add, and choose Audio or Video. On an empty list, click Import File. You can also drop audio files, video files, or folders onto the page.
  3. Wait for extraction and transcription to finish. Several files are transcribed one at a time in the background.
  4. Open the item and review the transcript and its processing status.
  5. Correct important speaker names, terms, and figures before you use the result.
You can also run the Transcribe command. Its settings include Output Format, Speaker Diarization, and Transcription Provider.

​
Use the transcript

Open a saved item to read the transcript, its summary, and Ask AI. Ask questions about the transcript instead of assuming every detail was recognized correctly. The provider and command you use decide whether you get timestamps, structured output, and speaker diarization. For vocabulary and speaker names, see Dictionary and Speakers. To find the transcript later along with your other documents, see Knowledge Base.

​
When transcription fails

Enconvo tells a transcription failure apart from a file with no speech. Read the error and its diagnostic details. A failure can come from audio extraction, the provider’s file limits, account access, or the service itself. Title generation and search indexing can fail separately from transcription. If the transcript is already saved, check whether only the title or indexing step failed before you import the same file again. Keep the original media until you have checked the transcript.

​
Troubleshooting

Speech Recognition

Choose a provider that handles files.

Meeting Recording

Record a meeting and transcribe it as people talk.

Live Captioning

See realtime subtitles while audio plays.

Dictionary and Speakers

Teach terms and name the voices in transcripts.