Quickly convert long call recordings and conference audio into text using batch recognition.
Advanced Media Co., Ltd. (Headquarters: Toshima-ku, Tokyo; Representative Director, Chairman and President: Kiyoyuki Suzuki; hereinafter referred to as "Advanced Media") has updated its development platform "AmiVoice Cloud Platform" that provides voice recognition API. , released "Asynchronous HTTP Speech Recognition API". Available from Friday, October 10th.
AmiVoice speech recognition API allows you to easily implement speech recognition functionality into your website or application without incorporating a special library into your client application.
In addition to the previously provided "WebSocket Speech Recognition API" for real-time speech recognition and "HTTP Speech Recognition API" for batch speech recognition, we have newly released "Asynchronous HTTP Speech Recognition API". Files larger than 16Mbytes, which is the limit of the "HTTP speech recognition API", can be recognized all at once, so long-term audio data such as contact center call audio, conference audio, video/radio/YouTube audio, etc. can be recognized at once. Suitable for transcribing. Since multiple files are processed asynchronously at the same time, recognition results can be obtained quickly regardless of the size or length of the audio file.
| ■WebSocket speech recognition API | Audio streams can be transcribed into text in real time. <Usage> ・Transformation of contact center conversations into text in real time ・Convert meeting remarks into text in real time ・Voice control of smartphones and IoT devices ・Voice dialogue system |
| ■Synchronous HTTP speech recognition API | You can convert audio files to text. Suitable for short audio files. <Usage> ・Converting short audio files such as voice memos and answering machines to text ・PoC of systems using voice recognition and evaluation of voice recognition accuracy |
| ■Asynchronous HTTP speech recognition API | You can convert audio files to text. Suitable for converting long audio files or large amounts of audio files into text. <Usage> ・Converting contact center call recording audio files to text ・Conversion of conference recording audio file into text ・Converting video files to text and creating subtitles |
Details about the three types of API are provided on the "AmiVoice Tech Blog".
https://amivoice-tech.hatenablog.com/entry/2021/10/08/
[Features of “AmiVoice Cloud Platform” speech recognition API]
1. No.1 voice recognition market share
■
AmiVoice is a highly accurate and high-speed speech recognition engine with over 20 years of accumulated know-how and data. It is used in a wide range of situations, including business situations and highly specialized work sites.
2. Starting from 1 yen for 99 hour. High quality voice recognition available at low cost
Pay-as-you-go billing based only on the amount of time spoken, not the amount of time recorded. Billing units are not rounded up to the nearest second. Starting from 1 yen per hour, you can use a high-quality speech recognition engine at the lowest price in the industry.
3. Achieving high recognition rates with engines that can be selected according to the industry and application
In addition to "general-purpose engines" that can be used in a variety of situations and businesses, we also have engines specialized for specialized terms and industry terms, such as those used in the medical field. In addition, we have a conversation engine that is strong against human conversation sounds such as face-to-face meetings, meetings, and web conferences, and an engine that is suitable for voice input to PCs and smartphones such as voice operations and email creation, depending on the usage scene. The recognition rate can be greatly improved by selecting an engine based on the selected engine.
| (AmiVoice Cloud Platform) | |||
| APP & WEB SOLUTION | https://acp.amivoice.com/main/ | ||
Advanced Media will continue to actively release and utilize various APIs and development kits, and work with a wide range of partners to expand our efforts to promote open innovation and create new usage scenarios.
*Source: ITR “ITR Market View: AI Market 2021” Voice recognition market sales share by vendor (2015-2021 forecast)
Above
