Test Audio Transcription with ElevenLabs

This example demonstrates how to use the ElevenLabs STT provider for audio transcription testing. It allows you to evaluate the accuracy and performance of ElevenLabs' speech-to-text capabilities within a structured testing framework.

Use this example when you need to rigorously test and compare the transcription quality of the ElevenLabs STT service. It is ideal for developers and QA teams who are integrating ElevenLabs into their applications and require objective performance metrics. Do not use this if you are looking for a general-purpose audio processing tool or if you do not intend to use the ElevenLabs STT provider.

The primary input for this example is audio data that will be transcribed by the ElevenLabs STT provider. The output will be the transcribed text, along with any associated metrics or results generated by the testing framework, such as accuracy scores or error rates, depending on the specific test configuration.

This example is designed to be used with promptfoo, an open-source tool for testing and evaluating LLM applications. promptfoo facilitates the setup and execution of these transcription tests.

This example is for developers, AI engineers, and quality assurance professionals who are evaluating or implementing speech-to-text solutions, specifically those considering or already using ElevenLabs. It differs from general STT testing by focusing on the ElevenLabs provider within the promptfoo ecosystem, offering a targeted evaluation.