Real-Time SaaS

<h2>Improvements</h2><ul><li>Faster Real-Time Transcription with More Consistent Latency<ul><li>Fewer words are included in each Final (typically 1-2 words per final).</li><li>The latency for final word transcriptions is now more consistent.</li><li>Average latency reduced by 300-400ms for a given max_delay.</li><li>We recommend re-evaluating the best max_delay for your use case. In most cases, you can reduce the max_delay and still get the same accuracy! Learn more about the accuracy vs. latency trade-offs <a target="_blank" rel="noopener noreferrer nofollow" class="link" href="https://docs.speechmatics.com/features/realtime-latency#accuracylatency-trade-offs">here</a>.</li></ul></li><li>Improved Partials<ul><li>Partials now include numeral formatting, enhanced punctuation, and better casing.</li></ul></li></ul>

2024.12.10 - Real-Time SaaS

Help Center

Batch SaaS

Batch Container

Real-Time 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

2024.12.10 - Real-Time SaaS

Improvements