Create a Parakeet Managed Inference Job
Create a speech-to-text Parakeet Managed Inference Job with the CLI.
Create a Parakeet Managed Inference Job from the CLI. Answer the prompts or pass flags, and CosmicAC deploys the speech-to-text model behind an OpenAI-compatible transcription endpoint.
Prerequisites
You need the following before you start:
- A running CosmicAC deployment. See Installation.
- The CosmicAC CLI installed and configured. See Install the CLI.
Steps
Create the job
Create the job interactively by answering prompts, or non-interactively by passing flags.
Start the interactive job setup:
cosmicac jobs createSelect Managed Inference (Parakeet) as the job type.
Set these fields:
- Job name: a name to identify the job.
- Tags: comma-separated labels for the job.
- Location: the region where the job runs.
- GPU type: the GPU to use. The CLI lists the GPUs available in your location.
- GPU count: the number of GPUs for one replica. One of 1, 2, 4, or 8.
- Model: the Parakeet model to serve,
nvidia/parakeet-tdt-0.6b-v3. - Chunk duration: the audio chunk length in seconds. Minimum
10. - Chunk overlap: the overlap between chunks in seconds. Must be less than the chunk duration. Minimum
5. - Max file size: the maximum audio upload size in MB. Minimum
1024. - Endpoint name: a name for the endpoint, used in its URL path.
- Replicas: how many copies of the model to run.
- Require Authorization header: whether callers must send an API key. See Create an API key.
- Notifications: the job lifecycle events this job reports. All four are on by default, and interactive mode prompts for them with a checkbox.
An event reaches your webhook only if it's also turned on in Settings → Notifications. See What controls delivery.
The Job configuration reference describes each field and its CLI flag.
Confirm the deployment
List your jobs to confirm CosmicAC created the job:
cosmicac jobs listThe job appears in the table with its ID, name, tags, and status. Wait for it to provision. The endpoint accepts requests once its status is running.
Help and troubleshooting
The job never leaves Creating or Starting
Find the job's container ID. The output lists Container ID for each container:
cosmicac jobs detail <jobId>CosmicAC names that container's KubeVirt virtual machine instance (VMI) <container-id>-n0. A multi-node job has one VMI per node.
Where you run kubectl against your cluster, list the VMIs in the namespace you set in K8S_NAMESPACE:
kubectl get vmi -n <namespace>If the VMI reports Running while CosmicAC still shows the job as Creating or Starting, cosmicac-wrk-agent-inference can't reach cosmicac-wrk-server-k8s-nvidia. The two connect directly, and some cluster networks block that connection.
To carry the connection through a relay, see Set up a relay for CosmicAC.