Transcribe Audio
Transcribe Audio using the CosmicAC CLI or curl.
Get a transcription from a Parakeet endpoint. Use the CosmicAC CLI with an audio URL, or curl with a local file or a URL.
Prerequisites
You need the following before you start:
- A running Parakeet Managed Inference Job with a serving endpoint. See Create a Parakeet Managed Inference Job Using the CLI.
- Your API key, if the endpoint requires an authorization header. See Create an API key.
- Audio to transcribe. The CLI accepts a hosted URL, and curl accepts a local file or a URL.
Steps
Find your endpoint name
List your endpoints:
cosmicac models statsEach endpoint appears as Endpoint: <endpoint-name>. Copy the name of your Parakeet endpoint.
Send the transcription
If you enabled Require Authorization header when you created the job, you need an API key. If you didn't, answer no to the CLI's API key prompt and omit the Authorization header from the curl request.
Start an interactive transcription session:
cosmicac inference transcribeAnswer the prompts, then send an audio file URL.
The cosmicac inference transcribe session asks for these values:
- Use an API key: answer yes to authenticate, then enter the key at the masked prompt.
- Endpoint ID: the endpoint name from the previous step.
- Audio file URL: the URL of the audio file.
After each transcription, the command asks for the next audio file URL. Press Ctrl+C to exit.