Cognitive Engines

Speech

Capture, identify, and categorize spoken words quickly, extracting insights automatically from unstructured audio and video files.

Transcription

Convert speech in audio or video files in 70 different languages and dialects into text transcripts.

Transcription — often referred to as speech-to-text or natural language processing (NLP) — engines in the Veritone cognitive engine ecosystem convert spoken words in audio and video recordings into readable and searchable text. They are built and trained to transcribe different languages and dialects.

FEATURES

Broad Language Support

Convert speech to text in 70 different natural languages and dialects in the cloud, with a subset that can be deployed locally, to support a diverse user-base, workforce, or population.

Text Transcripts

Export spoken word recordings as text transcripts in plain text, Microsoft Word, Timed Text Markup Language (TTML), WebVTT, and SubRip text formats via Veritone applications.

Machine & Manual

Choose the right option for your use case – machine transcription with AI or leverage aiWARE to manually transcribe your audio data via Veritone partners.

Searchable Results

Identify the keywords you are looking for quickly within transcripts with searchable transcription engine output via API or Veritone applications.

Near Real-Time Processing

Process audio and video files in near real-time for use cases requiring quick text extraction.

Files or Stream Support

Transform short-form or long-form audio into text in audio and video recordings, streamed recordings, or live data streams.

Flexible Deployment

Deploy in a new or existing application in the cloud via aiWARE GraphQL APIs, or with a subset that can be deployed on-premise via a Docker container. Learn more

Powered by an AI Ecosystem

Leverage advanced transcription machine learning algorithms from the Veritone managed cognitive engine ecosystem — including algorithms from Veritone, niche providers, and industry giants.

GET STARTED

$100 Cognitive Engine Processing Credit

Get instant access and a $100 credit* by signing up for a free Developer account.

*Veritone will apply a credit toward the first $100 incurred in each month for data ingestion and cognitive engine processing usage only.

Documents & Tutorials

Explore the documentation and tutorials to get started.

Speaker Detection

Partition audio files into segments to separate the words spoken by each speaker when.

Speaker detection – also known as speaker separation or diarization – engines in the Veritone cognitive engine ecosystem distinguish between multiple speakers in audio and video by partitioning recordings and streams into multiple segments according to speaker.

Speaker detection determines when speakers change and possibly which speakers are the same person, but it does not identify the speakers, like speaker recognition. Speaker detection and recognition engines can be used in concert.
 

Learn more about speaker recognition

Features

Speaker Separated Transcripts

Export spoken word recordings as text transcripts in plain text, Microsoft Word, Timed Text Markup Language (TTML), WebVTT, and SubRip text formats via Veritone applications.

Assign and Edit Speakers Detected

Assign labels to speakers, edit existing speaker labels, and delete labels and spoken words for specific speakers in speaker detection transcripts via Veritone applications.

Searchable Results

Identify audio segments where individuals of interest are speaking quickly with searchable speaker detection engine output via API and Veritone applications.

Near Real-Time Processing

Process audio and video files in near real-time for use cases requiring quick speaker detection turnaround.

Files or Stream Support

Detect speakers in short-form or long-form audio in audio and video recordings, streamed recordings, or live data streams.

Flexible Deployment

Deploy in a new or integrate into an existing application in the cloud via aiWARE GraphQL APIs, or with a subset that can be deployed on-premise via a Docker container. Learn more.

Powered by an AI Ecosystem

Leverage advanced speaker detection machine learning algorithms from the Veritone managed cognitive engine ecosystem — including algorithms from Veritone, niche providers, and industry giants.

GET STARTED

$100 Cognitive Engine Processing Credit

Get instant access and a $100 credit* by signing up for a free Developer account.

*Veritone will apply a credit toward the first $100 incurred in each month for data ingestion and cognitive engine processing usage only.

Documentation & Tutorials

Explore the documentation and tutorials to get started.

Speaker Recognition

Identify speakers in audio based on recordings of their voice.

Speaker recognition – often referred to as speaker identification – engines in the Veritone cognitive engine ecosystem identify when speakers change and who those speakers are in a piece of audio.

Speaker recognition expands upon the capabilities of speaker detection engines by identifying the individual whose voice was detected in addition to specifying the points of time in the file in which the person started and stopped speaking.

Learn more about speaker detection.

Features

Trainable with Custom Libraries

Create custom models using unique voice identifiers and metadata with the Veritone Library application or your own to identify a custom set of speakers in audio files. Learn more.

Near Real-Time Processing

Process audio and video files in near real-time for use cases requiring a quick speaker recognition turnaround.

Files or Stream Support

Recognize speakers in short-form or long-form audio in audio and video recordings, streamed recordings, or live data streams.

Flexible Deployment

Deploy in a new or integrate into an existing application in the cloud via aiWARE GraphQL APIs, or with a subset that can be deployed on-premise via a Docker container. Learn more.

Powered by an AI Ecosystem

Leverage advanced speaker recognition machine learning algorithms from the Veritone managed cognitive engine ecosystem — including algorithms from Veritone, niche providers, and industry giants.

GET STARTED

$100 Cognitive Engine Processing Credit

Get instant access and a $100 credit* by signing up for a free Developer account.

*Veritone will apply a credit toward the first $100 incurred in each month for data ingestion and cognitive engine processing usage only.

Documentation & Tutorials

Explore the documentation and tutorials to get started.

Contact Us