Summarize your audio data
In this guide, you'll learn how to use LeMUR to summarize your audio data with key takeaways.
If you want a Quickstart, see Apply LLMs to audio files.
To use LeMUR, you need an with a credit card set up.
Basic summary example
If you want to send a custom prompt to the LLM, you can use the LeMUR Task and apply the model to your transcribed audio files.
To summarize the content in your audio data, define a summarization prompt and call transcript.lemur.task(). The underlying transcript is automatically used as additional context for the model.
Example output
The transcript describes several common sports injuries - runner's knee,
sprained ankle, meniscus tear, rotator cuff tear, and ACL tear. It provides
definitions, causes, and symptoms for each injury. The transcript seems to be
narrating sports footage and describing injuries as they occur to the athletes.
Overall, it provides an overview of these common sports injuries that can result
from overuse or sudden trauma during athletic activities
Summary with specialized endpoint
The LeMUR Summary function requires no prompt engineering and facilitates more deterministic and structured outputs. You can use it with transcript.lemur.summarize().
You can add additional context to provide information that is not explicitly referenced in the audio data, as well as specify an answer format. For this, use the optional parameters context and answer_format.
Custom summary example (Advanced)
In this example, we'll run a custom LeMUR task with an advanced prompt to create custom summaries:
More summarization prompt examples
Try any of these prompts to get started:
| Summaries | "Summarize key decisions and important points from the phone call transcript" |
| Summarize audio segments | "Summarize the key events of each chapter" |
For more use cases and prompt examples, see LeMUR examples.
API reference
Improve the results
To improve the results, see the following resources:
- Optimize your prompt with the prompt engineering guide.
- To alter the outcome, see Change model and parameters.