Voci's Speech-to-Text technology leads the industry in speed, accuracy, and scalability
Our enterprise partners are using Voci’s highly accurate ASR technologies to gain an advantage over competitors and help thousands of customers better understand caller needs, provide superior service faster than ever, and boost overall operational efficiency.
Our GPU-accelerated, deep machine learning speech technologies feature open APIs to deliver greater insights to the contact center by transcribing audio into analyzable text.
Integrate highly accurate transcripts to meet the needs of your solution and your customers
Transcribe large volumes of recorded audio quickly via lightning-fast GPUs
Integrate highly accurate transcripts to meet the needs of your solution and your customers
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
Audio Compatibility
Supports the G.711 suite of audio standards (Uncompressed Pulse Code Modulation [PCM], μ-law, and A-law)
Deployment Method
In-cloud Deployment and On-Premise Deployment
Integration
REST API enables both batch (file-based) and real-time (stream-based) operation
Format
Open-format JSON and Text transcripts
Languages Supported
All North American languages (English, Spanish, and French)
Speech Engine
Large Vocabulary Continuous Speech Recognition (LVCSR)
Transcription Delivery Mode
Up to 150 hours of recorded calls per hour per single hardware unit
Flexible Pricing
Straightforward plans and high touch support to scale with your business