Skip to content

Custom ModelsView as MarkdownView this page as plain textOpen in ClaudeAsk questions about this pageOpen in ChatGPTAsk questions about this page

A custom model is a named collection of phrases that biases transcription toward domain-specific vocabulary, such as product names, technical terms, or internal jargon.

Custom models are available on the Realtime, Prerecorded, and Turns APIs.

Creating a Model

There are two ways to create a custom model:

  • Through the API, by specifying the phrases yourself. See the API reference for the endpoints to create a model and to add or delete phrases as the vocabulary evolves.
  • Through the console, by providing a prompt, files, and some context about your use case. A model is then created for you based on that input. See the console.

Models created through the console also show up in the API, so they can be inspected and managed there like any other model.

Using a Model

A custom model can be applied in two ways:

  • Configured on an API client, so every request made with that client uses the model by default.
  • Passed per request, via the custom_model_id query parameter on the Realtime, Prerecorded, and Turns APIs.

When both are set, the query parameter takes priority over the model configured on the API client.

Choosing Phrases

Good phrases are the terms the base model gets wrong: specialised vocabulary, uncommon names, brand and product names. Everyday words are already recognised well and only dilute the model.

Keep phrases focused

Biasing improves accuracy on audio that contains the phrases, but a large set of irrelevant ones can degrade transcription.

For short structured tokens like order codes and licence plates, use Patterns instead; they describe the shape of a token rather than a fixed phrase.