Automatic Speech Recognition API Reference
Note: Register now for Alexa Live, Amazon’s annual Alexa developer conference on July 20, 2022.
To evaluate the Automatic Speech Recognition (ASR) accuracy of your skill, you can use the ASR APIs. If you want to use the ASR Evaluation tool in the developer console, see the Automatic Speech Recognition (ASR) Evaluation tool.
ASR implementation steps
To run an ASR evaluation, implement the APIs in the following order.
- Create your audio catalog:
- Call Create a catalog to create your new catalog.
- Call Associate a catalog to a skill to associate your new catalog with the skill that you're evaluating.
- Create the upload for your catalog by calling Catalog content upload.
- Upload your .zip file of audio files to the S3 URL returned by Catalog content upload. Audio files must be .mp3, .wav, .aiff, or .ogg format.
- After the upload completes, call Complete Upload.
- Call Get Upload to get the ingestion status of your upload.
- Create your annotation set:
- Call the Create annotation set API to create your empty annoation set.
- Call the Update annotation set annotations API to add your uploaded audio utterances to the annotation set.
- Run the ASR evaluation by calling the Post ASR evaluation API.
- Return your ASR evaluation status and results by calling the Get ASR evaluation status API and Get ASR evaluation results API.
API reference list
- Create annotation set API – Call this API to create an empty annotation set. Fill the annotation set with pre-recorded utterances by calling Update annotation set annotations API.
- Delete annotation set API – Call this API to delete a specified annotation set.
- Delete ASR evaluation API – Call this API to delete the specified ASR evaluation, including in-progress evaluations.
- Get annotation set contents API – Call this API to download the annotation set contents in text/csv or application/json format.
- Get annotation set metadata API – Call this API to return the metadata for the specified annotation set.
- Get ASR evaluation results API – Call this API to return detailed ASR evaluation results.
- Get ASR evaluation status API – Call this API to return high level information about a specified ASR evaluation run.
- List all annotation sets API – Call this API to list all annotation sets for a given skill.
- List ASR evaluations API – Call this API to return historical Automatic Speech Recognition (ASR) evaluations.
- Post ASR evaluation API – Call this API to run ASR evaluations against an existing annotation set.
- Update annotation set annotations API – Call this API to update the annotations included for an existing annotation set.
- Error Reference – For errors that relate to all ASR APIs.