Speech to text software that’s flexible, scalable, and easy to use

icon-speech-to-text

Our GPU-accelerated, AI-based technology enables you to deliver greater insights to the contact center by transcribing audio into analyzable text.

Transcribe all calls quickly, accurately, and cost-effectively

017_GPU

Transcribe large volumes of recorded audio quickly via lightning-fast GPUs

005_analysis

Integrate highly accurate transcripts with your analytics or business intelligence platform

019_reduce-cost

Reduce your hardware footprint and minimize total cost of ownership

Features:

  • Cost-effectively scale from 10 to 100,000 agents
  • State-of-the-art NVIDIA® GPUs that increase compute performance and speech-to-text (STT) conversion speed
  • Optimized cloud solutions powered by AWS
  • Latest-generation Intel® Xeon® or AMD processors
  • High-speed DDR4 SDRAM for high-bandwidth data transfers
  • Containerized machines for VMware, AWS AMIs, and others

Technical Specifications

020_audio-compatibility
Audio Compatibility

Supports the G.711 suite of audio standards (Uncompressed Pulse Code Modulation [PCM], μ-law, and A-law)

009_deployment
Deployment Method

In-cloud Deployment

022_integration
Integration

REST API enables both batch (file-based) and real-time (stream-based) operation

023_format
Format

Open-format JSON and Text transcripts

024_supported-languages
Languages Supported

All North American languages (English, Spanish, and French)

025_speech-engine
Speech Engine

Large Vocabulary Continuous Speech Recognition (LVCSR)

007_complete-transcription
Transcription Delivery Mode

Up to 150 hours of recorded calls per hour per single hardware unit

Start building for free - Sign up for a demo