Real-Time Container

:::caution Warning This version should only be used alongside the GPU Inference Container. For more information and implementation detail, <a href="https://docs.speechmatics.com/on-prem/containers/gpu-inference-container" rel="noopener noreferrer" target="_blank">see here</a>. :::<ul><li>GPU based inference, only for English</li><li>Major accuracy gains for transcription (Standard and Enhanced operating points)</li><li>Major efficiency and speed gains, particularly for the Standard Operating Point</li><li>Improved Speaker Diarization accuracy for English (Standard and Enhanced operating points)</li><li>Improved Numeral Formatting in English</li><li>Improved formatting for common telephone numbers, measurements, websites, email addresses and credit cards</li><li>Alphanumerics now have upper-case letters</li><li>Added regional handling for en-AU and en-US output locale to keep 'pounds' as words</li><li>A number of other improvements and fixes for better readability</li><li>Resolved an issue where words would occasionally be fully upper-cased</li><li>Fix potential degradation in accuracy for multi-hour transcription sessions with low <code>max_delay</code> values</li></ul>

10.0.0 - Real-Time Container

Help Center

Batch SaaS

Real-Time SaaS

Batch Container

Batch Appliance

Real-Time Appliance

GPU Transcription Inference Container

GPU Translation Inference Container

Language ID Container

Real-Time Kubernetes

speechmatics

In Review

Planned

In Progress

Completed

Rejected

High Priority

Low Priority

Main Roadmap

Quarterly Roadmap

Monthly Roadmap

Tell speechmatics how they could make the product more useful to you.

Have something to say?

Hey {name|there}! 👋

Speechmatics

10.0.0 - Real-Time Container