Google has announced the general availability of a new visual interface for Google Cloud’s Speech-to-Text API in the Google Cloud console. The new visual interface aims to reduce the complexities developers face when they use the Speech-to-Text API.
The STT API allows developers to convert speech into text by leveraging Google’s years of research in automatic speech recognition and transcription technology. The API helps users add speech functionality to their applications to better serve consumer needs.
The STT API can be used from dictation and short commands to captioning and subtitles. However, to achieve the highest accuracy on any AI use case, STT requires careful testing and fine-tuning. Earlier, developers building on the STT API had to do this work manually, needed familiarity with GCP integration concepts and had to either build their own tools or manage various scripts and API calls to fully understand the API documentation. These actions made measuring, customising and improving models even more difficult
The availability of STT API within the Google Cloud Console simplifies the process, facilitating iteration and integration of models into developers’ applications by letting developers perform every API function from within the console. With this new addition, developers have the ability to manage and quickly iterate the STT model customisations with Model Adaption.
The STT API is available in all Google Cloud regions and can be accessed by all GCP users at no additional cost. The STT API supports over 70 languages in 120 different local variants.