Hey all 🍂

As Thanksgiving passes by, we’re feeling extra grateful for you—our amazing community. Your feedback, enthusiasm, and creativity drive us to keep pushing the boundaries of what’s possible with AI.

We’ve been cooking up some exciting updates to make your development life even better. Let’s dive in!

Hackathon Highlights

Earlier this month, Yoeven hosted a cozy hackathon in London, and it was a blast! We met incredible developers, exchanged creative ideas, and built some amazing prototypes together. Shoutout to everyone who joined; you made it unforgettable!

Follow us on X or join our discord to keep track of our live events!

What’s New

Fastest Speech-to-Text Solution on the Market

We’re thrilled to announce that JigsawStack’s speech-to-text API is now the fastest all around! In our recent benchmark comparison with Groq, AssemblyAI, and OpenAI, JigsawStack consistently delivered:

• 5s audio files: Processed in just 765ms, faster than AssemblyAI and OpenAI.

• 1hr+ audio files: Completed in 27 seconds, outperforming competitors on large files.

• Low cost: $0.05/hr with industry-leading speed and accuracy.

Read the full benchmark breakdown in our new article: JigsawStack vs Groq vs AssemblyAI vs OpenAI.

Join our Embedded Service

We launched a multimodal embedding model in Alpha! Most existing managed embedding services like text-embedding-3-large by OpenAI don’t support other modalities beyond text with pretty limited language support. We designed an embedding model to fill the gaps, it supports images, PDF documents, audio and text in over 80 languages.

→ Help test the model during Alpha and gain 4+ months free post-launch!

Drop Yoeven a DM on X or email him at yoeven@jigsawstack.com with your use case to get access.

Prompt Engine Upgrades

With Prompt Engine you can now handle larger inputs with increased token limits, enjoy smarter prompts that automatically optimize for better results, and access real-time information using AI Search. More power, same price—helping you take your AI workflows to the next level.

vOCR Now Supports PDFs

vOCR just got a massive upgrade! Now, you can extract high-accuracy data from PDFs alongside images and other documents. Perfect for workflows involving invoices, contracts, and more.

Caching Layer

API calls are now faster than ever with caching for key validation, file downloads and long running tasks. Smart caching allows all requests to revalidate dynamically preventing stale responses.

Why This Matters

These updates reflect our commitment to simplifying AI development and delivering tools that empower you to build faster and smarter. Whether you’re processing audio, handling PDFs, or embedding cutting-edge AI into your apps, we’ve got you covered.

Get Started Today

Explore the latest tools:

• Check our documentation for setup guides.

• Join us on Discord and X to connect with the community.

• Read the benchmarks to see how JigsawStack leads the way.

From all of us at JigsawStack, thank you for being part of our journey. We can’t wait to see what you’ll create next.

Cheers,
Angel & The JigsawStack Team