Transcribe Audio File
Transcribes a complete audio file or a part of it.
Google Speech Recognition Action
This integration allows you to automatically transcribe audio files in MP3, M4A, and WAV formats, supporting multiple languages and up to 10 minutes in length. It's ideal for efficiently converting spoken content into text.
By using this feature, you'll receive data such as the duration of the transcribed segment, the total duration of the file, the number of processed segments, and the complete audio transcription. Access to this functionality requires the Business Plan.
- Accepted formats: MP3, M4A, WAV
- Supports different languages
- Transcribe up to 10 minutes of audio
- Necessary Business Plan
Customization Options
Configurable fields you can adjust in your automation
- Audio File URL
- Audio File Format
- Language
- Start from Second number
- Duration
Information provided
When executed, this operation delivers the following data, which can be used in the same automatic task.
Tags
-
Range duration
{{range_duration}}
Total duration of the selected range to transcribe in seconds.
For example: 60 -
Source Duration
{{source_duration}}
Total duration of the audio file in seconds.
For example: 300 -
Total chunks
{{total_chunks}}
Total chunks
-
Text
{{transcription}}
Text string with audio transcript
-
Download duration
{{sec_to_download}}
Total duration in seconds used to download the audio file.
For example: 60 -
WAV Export duration
{{sec_to_wav_export}}
Total duration in seconds used to export audio file to WAV format.
For example: 45
Let's talk
Choose day and time.
We share the screen and answer all your questions.