The Gladia CLI provides a user-friendly way to test our API. It can be easily installed on any operating system (macOS, Windows, Linux), and supports all audio and video files formats.

Among the supported online formats:

  • Youtube
  • LinkedIn
  • Tiktok
  • Facebook
  • DailyMotion
  • Vimeo
  • Likee
  • ShareChat

The CLI also offers various options that can be enabled using flags. To view all available options and detailed documentation, please visit our CLI's GitHub page.

Here are some examples of CLI commands:

Example for a local file

gladia --audio-file split_infinity.wav  --diarization

Example for a remote file

gladia --audio-url --diarization

Going further with the CLI

./gladia --help

Usage: gladia [OPTIONS]

Transcribe an audio file or an audio URL using the Gladia API.

--audio-url TEXT URL of the audio file to be transcribed.
--audio-file TEXT Path to the audio file to be transcribed.
--language-behaviour TEXT Determines how to handle multi-language
--language TEXT Language spoken in the audio file.
--transcription-hint TEXT Hint to the transcription model. You can
pass names, topics, custom vocabulary, etc.
--noise-reduction Apply noise reduction to the audio.
--diarization Perform speaker diarization.
--diarization-max-speakers TEXT
Determines the maximum number of speakers to
be detected.
--direct-translate Activate direct translation to the specified
--direct-translate-language TEXT
Language to which to translate the
transcription, need to activate the direct
translation using --direct-translate.
--text-emotion Activate text emotion recognition.
--output-format TEXT Format in which to return the transcription
results. Possible values: table, json, text,
srt, vtt, plain.
--gladia-key TEXT API key for Gladia. Obtain it at
--save-gladia-key Save the API key to a configuration file.
--help Show this message and exit.