(AmiVoice Cloud Platform)

News
  • HOME
  • News
  • Asynchronous HTTP Interface v2 Issue (2026-07-01) [Resolved]

Asynchronous HTTP Interface v2 Issue (2026-07-01) [Resolved]

2026.07.01 Fault information

On July 1, 2026, an error occurred during speech recognition processing in the AmiVoice API's asynchronous HTTP interface v2, preventing the successful acquisition of recognition results.

The service has now been restored and is available for normal use.

Impact Range

  • Occurrence Date and Time: July 1, 2026, 00:00 (JST) to approximately July 1, 2026, 10:40 (JST)
  • Target service: AmiVoice API asynchronous HTTP interface v2

During the above time period, an Internal Server Error occurred during speech recognition processing for requests using the asynchronous HTTP interface v2.

*The asynchronous HTTP interface v1, synchronous HTTP interface, and WebSocket interface are not affected.

Cause

The issue stemmed from the expired license for the speech recognition server on the asynchronous HTTP interface v2 server.

While the licenses for the synchronous HTTP interface and WebSocket interface had been updated in advance, the license referenced by the asynchronous HTTP interface v2 was overlooked, resulting in the inability of the affected servers to perform speech recognition processing correctly from July 1, 2026, 00:00 (JST) onwards.

This was due to insufficient sharing of license management information between the development and operations teams, and a lack of a comprehensive process for verifying which licenses needed updating.

Remediation Actions

The license information referenced in the production environment was updated at approximately 10:23 (JST) on July 1, 2026. Subsequently, the server that had been running while still referencing the old license was stopped, and recovery was confirmed at approximately 10:40 (JST) on July 1, 2026.

Preventive Remediation & Process Improvements

We will revise the process to ensure that the update targets, scope of impact, and verification results are shared between the development and operations teams, and that no target services are overlooked.

In addition, we will revise the license renewal checklist to allow you to check the renewal status for all production services, including the synchronous HTTP interface, WebSocket interface, and asynchronous HTTP interface v2.

We sincerely apologize for any inconvenience caused to our AmiVoice API users.

Back to list
Use API for Free

Try out recognition accuracy

For engines, please try the latest End to End. If you would like an engine specialized for industries such as healthcare, insurance, or finance, please select Hybrid and choose your language model and acoustic model.

Engine

Language

Language models

Acoustic model

Example sentences will be displayed.
This is sample text. Your voice input will go here.
残 り 30 seconds left

Terms of Use for
AmiVoice Speech Recognition Demo

Select the language, language model, and acoustic model you want to try, press the "Start speech recognition" button, and start speaking.
You can speak freely or read out example sentences and the recognition results will be displayed.

*If you change the language, language model, acoustic model, or use application, please press the "Start speech recognition" button again.

Points to note

  • By using this service, you are deemed to have accepted the terms of use.
  • Supported browsers are the latest versions of Windows (Chrome, Firefox, Microsoft Edge), Android (Chrome, Firefox, Microsoft Edge), Mac (Safari), and iOS (Safari).
  • Depending on the browser, the recording quality may be poor. If you feel that the quality is not good, please try using a different compatible browser.
  • Please enable the microphone function in your browser's security settings.
  • The trial time for this service is 1 seconds per trial. If you would like to use it again, please click "Start speech recognition" button.
  • Voice data and text data may be used to improve speech recognition performance.
×