Speech

Speech input to machine translation APIs


Speech input, also known as voice input or audio input, is a feature of machine translation APIs required for speech translation.

There are different types of speech translation.

  • Live (simultaneous) speech translation
  • Offline (asynchronous) speech translation

Speech input can be combined with different types of output.

  • Speech-to-speech machine translation (dubbing)
  • Speech-to-text machine translation (subtitles)

Often, speech recognition (transcription) and translation are separate APIs or API calls, that can be combined to effectively support speech translation.

Speech translation APIs are typically slower than text translation APIs.

API support

machine translation APIs support speech translation.

Want to learn more about Speech?


Edit this article →

Machine Translate is created and edited by contributors like you!

Learn more about contributing →

Licensed under CC-BY-SA-4.0.

Cite this article →