High-Performance Speech Recognition AI 'mocoVoice API' Now Supports Multiple Languages!

We are pleased to announce that the high-performance speech recognition AI "mocoVoice API" provided by mocomoco Inc. now supports 99 languages.

In addition to our existing Japanese and English support, the API can now process languages from around the world, including major languages such as Korean, Chinese, Spanish, German, and French.

Furthermore, it accurately recognizes "code-switching" speech where multiple languages are mixed, achieving highly precise transcription. This is expected to further enhance efficiency in global business and multinational communication settings.

To start using the mocoVoice API, please apply using the form below.
mocoVoice API Application Form

＜New Feature Highlights＞

Multilingual support for over 99 languages

Supports not only major languages such as Korean, Chinese, Spanish, German, and French, but also region-specific languages.
For details on supported languages, please click here.

Code-switching support across multiple languages

Code-switching support that automatically detects language changes during a conversation (e.g., Japanese → English → French) and transcribes them appropriately for each language.
Facilitates seamless meeting minute creation even in multilingual environments, such as international conferences and meetings with overseas offices.

＜Use Case Examples＞

Meeting minutes for international conferences and multinational teams Summarize discussions held in various languages so the entire team can accurately grasp the content.
Recording meetings with overseas business partners Streamline information sharing by collectively transcribing audio that mixes Chinese, Korean, English, and other languages.
Generating subtitles for global webinars Utilize for real-time subtitles and content archiving, contributing to higher satisfaction at international events.
International events with multiple speakers Combine speaker diarization with multilingual support to accurately and clearly record each speaker's remarks.

＜About mocoVoice API＞

mocoVoice API is a service that integrates high-precision speech recognition based on OpenAI Whisper with mocomoco's original proprietary technologies below.

Proprietary dictionary function No need to specify the phonetic reading when pre-registering technical terms and proper nouns. Accurately handles industry-specific terminology.
Multimedia support Capable of extracting and recognizing audio from video files as well as audio files.
Multilingual, speaker diarization, and code-switching support at no additional cost These features are included in all plans and can be used flexibly depending on your needs.

＜Pricing Plans＞

"Multilingual support," "speaker diarization," and "code-switching" features are available in all plans at no additional cost. For details, please check here.

＜Future Outlook＞

Upcoming mocoVoice demo page We are currently preparing a demo page that anyone can easily try out!

＜Service Application＞

To start using the mocoVoice API, please apply using the form below. You can try out the new features immediately after creating an account.
mocoVoice API Application Form