Create a Parakeet Managed Inference Job in the web interface

Open the new job form

In the left navigation, click Jobs, and then click New Job.

Select the job type

In the What kind of job? section, select Managed Inference, and then click Continue.

Enter the basics

In the Basics section, enter a Job name. Use lowercase letters and hyphens.

In Tags, add at least one tag. To add a tag, type it, and then press Enter or type a comma.

Click Continue.

Select the model

In the Model to serve section, select nvidia/parakeet-tdt-0.6b-v3. CosmicAC prefills the Parakeet configuration from the model's recommended configuration. The configuration has the following fields.

• Chunk duration: the seconds of audio in each chunk, with a minimum of 10.
• Chunk overlap: the seconds of overlap between adjacent chunks, with a minimum of 5. The overlap must be less than the chunk duration.
• Max file size: the maximum upload size in MB, with a minimum of 1024.

A Parakeet recommended configuration stores no runtime image, data type, quantization, tensor parallel, or reasoning parser, so the form doesn't show those fields. CosmicAC supplies the speech-to-text runtime image from the job type.

Name the endpoint

Under Endpoint, enter an Endpoint name. The name must be unique across the active Managed Inference Jobs in the deployment. A failed job keeps its name until you delete the job.

Set the root disk

Under Instance resources, set the Root disk (GB). Select a preset or enter a value. Increase it for a large checkpoint that exceeds the cluster default.

Require an API key

Under API key required, select Require Authorization header, and then click Continue. To create an API key that authenticates requests to the endpoint, see Create an API key in the web interface.

Select the hardware

In the Hardware section, select a Location first. The GPU list stays empty until you select one.

Select a GPU from the ones available in that location. Each card shows the GPU's VRAM, CPU, and RAM. Set the GPU count, and then set the CUDA / driver. Below the count, Recommended for this model shows the model's GPU count. On one node is the most free GPUs on any single node, and In this region is the total free across the location.

Set Replicas to 1, 2, or 4. CosmicAC doesn't autoscale replicas, and a job keeps the count it starts with. A Parakeet replica always runs on one node. For how requests reach the replicas, see Replicas.

Click Continue.

Select the notification events

In the Notifications section, turn on each job lifecycle event that you want this job to report. CosmicAC turns all four on by default.

• job.failed: the job transitions to Failed, and the event carries the failure reason.
• job.degraded: healthy replicas drop below the count you set, and the endpoint stays live.
• job.recovered: the job returns to Active from Degraded or Failed.
• job.restart_storm: any replica restarts three times within 10 minutes.

These preferences cover this job alone. An event you turn on here reaches your webhook only if it's also turned on in Settings > Notifications, which also controls the model health and usage window events for the whole deployment. See Set up webhook notifications.

Click Continue.

Review and create the job

In the Review & launch section, check that it reports Ready to create, and then click Create job. If it reports issues instead, click Edit on the row that names the problem, fix it, and then return to this section.

Open the endpoint

In the Provisioning status dialog, click Open job. When the job is running, click the Endpoint tab to view the endpoint URL. To send audio to the endpoint, see Transcribe audio.