Skip to main content

​
Cloud AI Models

​
Allow Cloud AI Models Toggle

From the Models tab in your dashboard, you can control whether your members are allowed to use Superwhisper’s hosted cloud models. When enabled:
  • Members can use Superwhisper’s online AI models for transcription
  • No additional configuration required
  • Models are hosted and maintained by Superwhisper
When disabled:
  • Members can only use custom models that you configure
  • Useful for organizations requiring all AI processing through approved vendors
  • Ensures data only flows through your organization’s configured providers
Model Management Interface

​
Custom Models

​
Overview

Custom models let your members use specific AI models from any provider you configure.

​
Adding a Custom Model

To add a custom model:
  1. Navigate to the Models tab in your dashboard
  2. Click the + Custom Model button at the top right
  3. Select your provider from the dropdown list, or Custom if your provider is not listed
  4. Input your API Key for your provider, if applicable we will attempt to fetch models you have access to in your instance
Your API Key is encrypted at rest for security
  1. Input other model details, and save
    • Name - A friendly name for the model (e.g., “GPT-5 Pro”, “Anthropic Testing”)
    • Model ID - The provider’s model identifier (e.g., gpt-5-mini, claude-sonnet-4-5-20250929)
    • API URL - The endpoint URL for the model API
Each selected provider will have reference documentation linked at the bottom of custom model create Provider Select Complete Model Once configured, your custom models will appear in the Custom Models table and can be modified / deleted

​
Custom Model Distribution

Members receive access to your configured models every time they start the app. They can pick which model to use when setting up each mode. Custom Model Selection

​
Use Cases

​
Cloud Models Only

Enable “Allow Cloud AI Models” and don’t configure any custom models. The default setup. Members use Superwhisper’s hosted models with no extra configuration.

​
Custom Models Only

Disable “Allow Cloud AI Models” and configure one or more custom models. All AI processing goes through your approved providers with your own API credentials.

​
Hybrid Approach

Enable “Allow Cloud AI Models” and configure custom models. Members choose between Superwhisper’s hosted models and your custom ones based on their needs.

​
Troubleshooting Custom Models

Most custom model issues come from a mismatch between the API URL, the model ID, or the API key. Use the table below to map the error you’re seeing to a likely cause.
ErrorLikely causeWhat to check
401 Unauthorized / Invalid API keyAPI key wrong, expired, or scoped to a different projectRegenerate the key in your provider’s dashboard, paste it fresh, check key scope
403 Forbidden / Provider rejected the requestKey is valid but doesn’t have access to that specific model or deploymentConfirm the model is enabled on your provider account; for Azure, confirm the deployment exists and the key has access to it
404 Not Found on the API URLEndpoint URL is wrong or missing a path segmentSee provider-specific notes below
404 on the modelModel ID doesn’t match what the provider expectsFor Azure, use your deployment name, not the model name. For OpenAI-compatible endpoints, copy the exact ID from the provider docs
429 Too Many RequestsRate limit or quota on the provider accountCheck usage limits on the provider dashboard
Timeout / no responseEndpoint unreachable from the user’s networkConfirm the endpoint is publicly reachable, or that your VPN allows it

​
Azure OpenAI

  • API URL format: https://{resource-name}.openai.azure.com/openai/deployments/{deployment-name}/chat/completions?api-version=2024-02-15-preview
  • Model ID: use the deployment name you created in Azure AI Studio, not the underlying model name (e.g., gpt-4o-mycompany, not gpt-4o)
  • The deployment must be created and in Succeeded state before adding it in Superwhisper

​
OpenAI-Compatible Endpoints

  • API URL format: the base URL up to and including /v1 (e.g., https://api.together.xyz/v1)
  • Model ID: the exact model slug from the provider’s docs
  • The endpoint must implement /chat/completions to work with Superwhisper

​
Self-Hosted Endpoints

  • The endpoint must be publicly reachable from the user’s machine. Endpoints behind a corporate VPN will only work for users on that VPN
  • TLS is required. HTTP-only endpoints won’t connect
If the error persists, email enterprise@superwhisper.com with the provider, model ID, and the exact error message.

​
Support

Questions about model management or custom model configuration? Email enterprise@superwhisper.com, request a shared Slack channel, or schedule a call.