Scale quickly, globally with dynamic audio translation
Proven record of quality
Google Cloud’s translation and speech recognition technologies have been widely recognized for their quality, thanks to Google’s machine learning expertise. Bringing cutting-edge technologies together, Media Translation API provides you with state-of-the-art audio translation along with the features of our popular Translation API and Speech-to-Text API.
Seamless content translation
Translate content directly from your audio data. Media Translation API enhances the accuracy of interpretation by optimizing model integrations from audio to text and abstracts potential frictions you may face initiating multiple API calls. Simply make one API call, and Media Translation takes care of the rest.
Streaming translation at speed
Stream translation output as you supply audio from a microphone or prerecorded audio file. Media Translation API minimizes the latency between input and translation results—enhancing user experience and enabling real-time engagement across languages and/or geographies.
Real-time translation is available during streaming audio input from a microphone or prerecorded audio files, and the API optimizes the integration for reduced latency.
The API accurately punctuates your translation results (e.g., commas, periods, question marks).
Media Translation API comes with two enhanced models (video, phone call), so you can optimize accuracy for your specific audio use case.
Media Translation API supports 12 languages.
At OnePlus, we aim to share the best technology with the world, hand in hand with our users. One important feature for our product is face-to-face communication across countries, time zones, and even languages. With Google Cloud’s Media Translation API, we are now able to provide real-time streaming translation for video chat with a simple API integration and ensure our customers feel effortlessly connected with minimal latency.Gary Chen, Head of Software Product, OnePlus
Media Translation API is priced monthly based on the amount of audio translation successfully processed by the service and on the model used for translation. Usage is measured in increments rounded up to 15 seconds.