Nov 12, 2020 | Read time 2 min

Speechmatics launches industry-first Global Spanish language pack for automatic speech-to-text transcription at scale

Speechmatics’ Global Spanish speech recognition lanaguage pack rivals competitors in accuracy across a range of accents and dialects.
languages 4
Speechmatics
SpeechmaticsEditorial team
Testing found that for all variations of Spanish, Speechmatics’ GS language pack was the best option in every instance.

Speechmatics, a UK leader in any-context speech recognition technology, today launches the first Global Spanish language pack on the market that supports all major Spanish accents.

Global Spanish (GS) is a single Spanish language pack trained on data drawn across a wide range of diverse sources – specifically those from Latin America – making it the most accurate and comprehensive accent-independent Spanish language pack for speech-to-text.

Compared directly, GS was between 3% and 20% more accurate than all Google’s Beta accent-specific language packs and between 4% and 13% more accurate than Microsoft’s Video Indexer accent-specific language packs. * Speechmatics utilized the latest advancements in machine learning and applied proprietary language training techniques to create the GS language pack. With Speechmatics’ GS model, businesses using speech recognition for Spanish voice data won’t have to jump between multiple language packs to optimize the accuracy of their transcriptions, reducing costs and streamlining operations.

The Speechmatics approach delivers a simpler user experience with no additional software or complex processes needed. Following the success of its Global English language pack, Global Spanish is fast, accurate, reliable and more flexible, convenient and inclusive.

Ian Firth, VP Products at Speechmatics comments:

“With Spanish being the second most natively spoken language across the world, it was time that businesses had access to an all-encompassing language pack to help streamline the transcription process and increase accuracy.

Our pack does just that by accommodating multiple accents, dialects and regional variations. By defying the industry convention of single accent-centric packs, Speechmatics is on a journey to make all languages truly accessible to businesses with our global language approach.”

Lee Worth, ASR & Live Captioning Operational Excellence Lead at Red Bee Media comments:

“At Red Bee Media, we regularly assess all ASR solutions to ensure our captioning services are built on the strongest possible foundations. Speechmatics’ engine has shown recent average improvements of 10% in English and 20% in Spanish, on top of already-excellent accuracy.

It’s clear Speechmatics have worked hard to increase their Global English and Spanish engines’ recognition of an increasing range of accents and dialects, which will enable us to further improve both our pre-recorded captioning workflows and our market-leading automated live captioning services.”

With approximately 500 million speakers globally, Spanish is the fourth most spoken language overall. Approximately 90% of Spanish spoken in the world is in the United States, Mexico, Central and South America, with the remaining 10% in Spain.

*Test sets comprised of almost 8.5 hours of diverse audio and transcribed text covering multiple use cases. Accented test files included variations in gender, age, region and ethnicity of speakers.

Want to see more content like this? Sign up for our newsletter!

Latest Articles

Carousel slide image
Product

Alphanumeric speech recognition: why voice assistants mangle SKUs (and how to fix it)

A guide for voice AI engineers, ecommerce platforms and warehouse teams on SKU recognition accuracy voice assistant deployments depend on: why speech recognition systems produce transcription errors on product codes, what to measure when error rates matter, and the fixes that move the needle on order picking, voice ordering and customer-facing voice AI.

Speechmatics
SpeechmaticsEditorial Team
Carousel slide image
Technical

The Adobe story: How we made cloud-grade AI work on your laptop

Behind the build: what it takes to make cloud-grade speech recognition work inside Adobe Premiere, and why Whisper raised the stakes.

Andrew Innes
Andrew InnesChief Architect
Carousel slide image
Company

Adobe and Speechmatics deliver cloud-grade speech recognition on-device for Premiere

Adobe Premiere users can run the most accurate on-device transcription locally; efficient enough for a laptop, powerful enough for professional work.

Speechmatics
SpeechmaticsEditorial Team
Carousel slide image
Use Cases

Best speech-to-text AI guide: APIs, platforms and services compared

Speech-to-text has moved from novelty to enterprise infrastructure. Here's how the leading platforms stack up in 2026 — and how to pick the right one.

Tom Young
Tom YoungDigital Specialist
Speechmatics x Thymia combine medical-grade speech-to-text with clinical-grade voice biomarker intelligence to identify health signals.
News

AI can now understand health signals from 15 seconds of your voice, including fatigue, stress and type 2 diabetes

The joint platform returns transcription and health signals in real time, with no additional hardware required.

Speechmatics
SpeechmaticsEditorial Team
[alt: Concentric circles radiate outward from a central orange icon with a white Speechmatics logo. The background is dark blue, enhancing the orange glow. A thin green line runs horizontally across the lower part of the image.]
Technical

Speed you can trust: The STT metrics that matter for voice agents

What “fast” actually means for voice agents — and why Pipecat’s TTFS + semantic accuracy is the clearest benchmark we’ve seen.

Archie McMullan
Archie McMullanSpeechmatics Graduate