Speech

Our platform gives access to a large number of speech and audio analysis technologies from the best providers.

Get Started

Speech-to-text

This technology (also automatic speech recognition) is used to automatically transcribe audio (or video) files and extract the text to be analyzed afterwards.

Custom speech-to-text

Unlike the pre-trained speech-to-text engines, this technology allows to generate a customized transcription engine specially trained on the user's labeled data.

Text-to-speech

This technology makes it possible to generate audio from a text while choosing the associated voice (male or female voice, etc.)

Speech diarization

This technology is used to separate several voices in an audio and to specify the precise moments when each individual speaks.

Speech analysis

This technology (also called opinion mining) automatically analyzes the feelings and emotions associated with an audio or a video.

Language detection

This technology automatically defines the most likely language in which an audio is expressed. It can then be translated for example.

Speech identification

This technology enables the association of information describing the voice being analyzed: estimation of sex, age, etc. It is also possible to use it to identify a person.

Speech translation

This technology allows a speech in an audio to be translated directly from one defined language to another.

Try Eden AI for free.

You can directly start building now. If you have any questions, don't hesitate to schedule a call with us!

Get started