Things are moving fast. We launched JigsawStack v3, hosted another Smol Models Hackathon, shipped major improvements, and made our debut on Product Hunt. Here’s a quick recap, plus everything new and what’s coming next.

Hackathon Recap

We wrapped our second Smol Models Hackathon in San Francisco and it delivered.

Devs spent the day experimenting, connecting, and shipping creative prototypes using JigsawStack. From first-time builders to experienced founders, the energy was strong all the way through demo time.

Thank you to all who came through- we’ll see you at the next one soon!

What’s New?

v3 brings faster APIs, unified endpoints, and major pricing improvements. Here we highlight a few of our favorite changes in a fun way:

• AI Web Scraper that handles dynamic, static, and infinite scroll pages

• AI Web Search that finds anything, anywhere

• Token-based billing — up to 36x cheaper

See it in action →

Gemini vs JigsawStack vOCR

We benchmarked Google’s Gemini OCR against JigsawStack vOCR on real-world tasks:

• Multilingual signs

• Structured PDFs

• Receipts

• Handwritten text

JigsawStack vOCR delivered stronger accuracy, richer structure, and faster responses.
Try it out in our interactive Google Colab Notebook.

Read the full comparison →

Translate Text in Any Image

Our new Image Translation API lets you extract, translate, and overlay foreign text right back into images. While also keeping the images original style. Great for:

• Travel and tourism apps

• Product localization

• Educational tools and research

Explore how it works →

Other Improvements Since v3 Launch

• Speech-to-Text: Faster speaker detection and cleaner transcript splits

• vOCR: Improved accuracy on high-res and complex documents

• Bug Fixes: Performance boosts across OCR, Translate, and Embedding

• SDK Updates: NSFW file support and more on the way

Big Thank you to the Community!

Our Product Hunt launch brought in great feedback and support from devs around the world.

If you missed it, you can still check it out here:
View the launch →

Want to Get Involved?

Here are a few ways you can join in and maybe get featured in our next update:

• Submit your build → Reply to this email or share it on X. We’d love to feature you!

• Join our next hackathon → Coming soon (Bay Area)

• Contribute to docs or SDKs → Found a bug or missing example? PRs welcome 🙌

Thanks for building with us. Whether you're experimenting on the weekends or shipping to production, we're here to make backend AI infrastructure simple, powerful, and accessible.

Cheers,
The JigsawStack Team
support@jigsawstack.com | Join our Discord →

👋 Meet the Team & Upcoming Hackathon!

Exciting news! We finally met in person for the first time in San Francisco, and had a blast! We're keeping the momentum going with our upcoming hackathon:

Smol Hackathon for Smol Models v0.2

• 

  📅 Date: Saturday, April 19th

• 🕒 Time: 9:30 AM - 6:30 PM

• 📍 Location: Hacker House, Nob Hill, San Francisco (exact address upon approval)

What to Expect:

• Cozy hacker-house vibes to kickstart your weekend AI projects

• Opportunities to explore new AI tools, features, or product integrations

• Casual atmosphere for sharing work and receiving feedback

• Demos, small talks, and networking with fellow devs

Schedule:

• 9:30 AM: Doors open

• 10:00 AM: Introduction & tech sharing

• 11:00 AM: Start building

• 5:30 PM: Demos

• 6:30 PM: Doors close

👉 Register here (approval required)

Got questions? Reach out to Yoeven on X!

Support Us on Product Hunt!

We’re excited to announce that JigsawStack v3 is launching on Product Hunt on April 21st! Your support would mean the world to us. Mark your calendars, and join us on launch day to help spread the word, share your feedback, and upvote our launch! 🚀

Click here to get notified on the 21st!

What's New in v3?

New Token-Based Pricing Model is Live

Our new pricing is now active and automatically applied to your account:

Pricing details:

• Input & Output Tokens

• Inference Time Tokens (1ms processing = 1 token)

This granular pricing means most users will experience cost savings ranging from 2.5x to 36x compared to our previous per-request pricing!

Service Merges

• AI Scraper & Web Scraper are now combined

• All Geo APIs have been removed

New Model Launches

• Embedding model (v1 beta)

• Image-to-Image Translation model

Key SDK Updates in v3

AI Scraper: Enhanced parameters for precise data extraction.

jigsaw.ai_scrape({
  url: "https://example.com",
  selectors: ["h1", ".product-description"],
  element_prompts: ["titles", "Product descriptions"],
});

Embedding API: Seamlessly integrate embeddings for diverse data.

jigsaw.embedding({
  text: "Your text here",
  type: "text",
});

Image-to-Image Translation: Easily translate image content.

jigsaw.translate.image({
  url: "https://images.unsplash.com/photo-1566657817181-c69e4a8eeb1e?q=80&w=3087&auto=format&fit=crop&ixlib=rb-4.0.3&ixid=M3wxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8fA%3D%3D",
  target_language: "hi",
});

Important Note: The updated JavaScript and Python SDKs include breaking changes. Be sure to check our updated documentation to navigate these updates smoothly.

More Highlights from Recent Updates:

• Secured $1.5M funding from Ada Ventures and Antler

• Welcomed Harsha Vardhan Khurdula as our Founding AI Researcher

• Benchmarking shows JigsawStack vOCR outperforming Mistral OCR

• Added powerful web crawling capabilities

• Launched the JigsawStack MCP Server for seamless agent integration

What's Coming Next?

We're rolling out continuous enhancements throughout April and May. Keep an eye on your inbox for more exciting announcements!

Need Support?

Our team is ready to help with any questions or feedback:

• support@jigsawstack.com

• Join our Discord

• Check our updated documentation

Thank you for being an essential part of our growing developer community!

Cheers,
Angel & The JigsawStack Team

Hope you’ve been well! It’s been a big month for us at JigsawStack. Between funding milestones, major product updates, team expansion, and community events, we’ve been moving quickly on all fronts.

Let’s get into what’s been happening.

First, we’re excited to welcome Harsha Vardhan Khurdula as our new Founding AI Researcher! Harsha will be leading model training, fine-tuning, and benchmarking. In his own words, he’s ready for “endless training loops and the occasional glitch that reminds us even AI has off days.” He’s already off to a strong start.

Funding Milestone: $1.5M Raised

We’re proud to share that JigsawStack has raised a total of $1.5M, with our most recent $1M round led by Ada Ventures. This follows our earlier pre-seed from Antler.

Michael Tefula from Ada Ventures has been an incredible partner, within minutes of meeting, he pulled out his laptop, installed the SDK, and began sending API requests on the spot. That energy is exactly what we’re building for: developers who want fast, seamless AI infrastructure they can trust.

You can read more about why Ada invested here.

Benchmarking

JigsawStack vOCR vs Mistral OCR
We put our vOCR model up against Mistral OCR in a series of tests covering multilingual text, handwriting, document structure, and bounding box accuracy.

Mistral OCR struggled with handwritten content and lacked bounding box support. Meanwhile, JigsawStack vOCR extracted text with high precision—even from noisy, multilingual, or handwritten sources—and returned structured outputs with full position data.

You can explore the full comparison here.

JigsawStack STT vs OpenAI Audio STT
After OpenAI’s latest update to Whisper, we ran a comparison using real-world audio files.

JigsawStack’s Speech-to-Text delivered faster results, supported speaker labels out of the box, and offered cleaner structured output—without sacrificing accuracy. If you're working with meetings, voice notes, or podcasts, our transcription model is built for both speed and clarity.

Read full breakdown here.

Documentation and SDKs Refreshed

We’ve updated the JigsawStack SDKs in TypeScript, Python, and cURL, and overhauled our documentation to make onboarding smoother. There are now clearer error messages, new CLI tooling, and expanded code samples.

Instant Tool Demos on Product Pages

You can now try any of our models directly on the API landing pages—no signup or login needed. Each tool comes with 20 free requests per day for testing. This is especially helpful for no-code builders or developers exploring fast prototyping.

AI Web Scraper Now Supports Web Crawling

The AI Scraper has evolved. It now supports full web crawling with automatic link discovery, infinite scroll handling, custom headers, and proxy support. Whether you’re scraping structured data from pricing pages or crawling an entire site like Wikipedia, the process is now as simple as giving a few prompts and running one API call.

We’ve put together a blog walking through how it works here, and you can try it live on the Scraper product page. No login required.

Vibecoding with AI Coders

This month, I tested the top three AI coding assistants—Luvable, v0, and Bolt—by building the same JigsawStack app with each. Some flew through it, others needed a bit more help.

From API setup to debugging, I break down what worked and what didn’t.

Check out full video here.

MCP Server Now Available

We launched the JigsawStack MCP Server—our open-source implementation of the Model Context Protocol (MCP) that allows any compliant agent (like Claude Desktop or Smithery) to use our tools on demand. You can now plug JigsawStack’s services into autonomous agents, without hardcoding API logic.

More about it here, or check out the GitHub repo.

Looking Ahead

Thanks for being on this journey with us. These updates represent a significant leap forward in our mission to simplify backend AI. We’re building a platform that helps developers move fast without friction—tools that work out of the box and scale when you need them to.

If you’re experimenting with JigsawStack or thinking about integrating it into your project, we’d love to hear what you’re building. You can always reach us on X, Discord, or just by replying directly.

Talk soon,
Angel & The JigsawStack Team

We have some amazing updates to share with you all! From the launch of OmiAI to powerful enhancements in our AI tools, we’re making AI development easier, smarter, and more efficient.

What’s New?

Introducing OmiAI

Say hello to OmiAI, an opinionated AI SDK for TypeScript that auto-picks the best model for your prompts from a curated suite of LLMs. No more over-configuring—just prompting.

Why OmiAI?

✅ Curated model selection for best quality, speed & cost
✅ Auto model chaining for complex tasks
✅ Built-in reasoning (o3-mini, DeepSeek r1)
✅ Internet access in real-time
✅ Multi-modal support (PDFs, images, audio, CSV, JSON, etc.)
✅ Seamless model fallbacks & retries
✅ Powered by Vercel's AI SDK & JigsawStack tools

Quick Install:

npm i omiai

Learn more here & view models used here.

Updated AI Web Scraper

Our AI Web Scraper just got an amazing update! Now, scraping and crawling the web is more seamless than ever:

✅ AI Web Scraper now returns all links on a page—perfect for web crawlers
✅ Autoscroll now on AI Web Scrapper to ensure full-page coverage
✅ Increased goto option max to 40 seconds for broader page coverage
✅ waitFor option max increased to 40 seconds for better scraping precision

Check out the updated docs here.

Image-to-Image Translation Model

We're working on an Image-to-Image Translation Model that extracts, translates, and overlays text back into images while preserving their original style. Our first version focuses on OCR, translation, inpainting, and overlaying text.

The long-term goal is to train a diffusion model for high-quality translations in multiple scripts, including Hindi, Arabic, and Chinese. We’re experimenting with different solutions and would love to hear your thoughts!

Learn more here.

New SDK Install Option – Now Supports Bun!

Developers using Bun can now install JigsawStack with:

bun i jigsawstack

Join the conversation on our Discord or X to let us know what Install Options you’d like to see next!

Stay Ahead in 2025

We’re committed to pushing AI boundaries with tools that simplify workflows and boost efficiency. Expect more updates soon and thank you for being part of our journey!

Also, We’re hiring! If you’re a Full Stack Engineer join our mission to redefine AI development.

Cheers,
Angel & The JigsawStack Team

As we step into 2025 and celebrate both the New Year and upcoming Chinese New Year — Gong Xi Fa Cai 🧧! We are wishing everyone a prosperous and successful year ahead and are thrilled to share some transformative updates to JigsawStack.

Following an incredible year of growth and innovation in 2024, we're taking another bold leap forward with the launch of Version 3.

Let’s dive into what’s new and what’s ahead!

What’s New?

Image Generation API – Simpler, Smarter

No more wrestling with complex configurations. Our new Image Generation API takes your prompt and automatically selects the best model from a robust suite like Flux, Stable Diffusion, and more. Less setup, more results!

AI Video Search Engine + Multimodal Embedding Model

Explore the AI Video Search Engine, now powered by our Multimodal Embedding Model, which supports text, images, audio, PDFs, and 80+ languages. Designed for diverse applications, it’s your solution for seamless retrieval across different formats and languages.

Check out the docs here - Alpha testers get free access during testing + 4 months free post-launch!

2024 Wrap-Up Video

We’re grateful for an amazing 2024 and excited for what’s next! Watch our Year in Review to see highlights here.

Big Changes Coming with v3

1. Less is More

Simplified workflows, smarter decisions. Like Prompt Engine, our tools will make the best choices for you with minimal configuration.

2. More Open Source

Expect more contributions to the community with open frameworks, dev tools, and models.

3. Native AI

Our models process raw data directly (e.g., summarizing PDFs without preprocessing text)—improving quality, cost, and developer experience.

Other Updates

Prompt Engine Limit Increase: Input limit boosted from 30k to 500k characters—more space for complex workflows.

Enhanced Summarization for Your Data: Dealing with large volumes of text? Simplify your workflows with our enhanced Summary API. Perfect for legal documents, meeting notes, or articles. Learn more here.

Python SDK Async Client: Simplify development with fully-typed parameters, built-in file handling, and webhook support.

pip install jigsawstack

Explore SDK Features

Join Us

We’re hiring! If you’re an AI researcher or Full stack engineer, join our mission to redefine AI development.

Thank You

2025 is already shaping up to be an incredible year. We couldn’t do this without your support, feedback, and creativity. Let’s build the future of AI together!

Cheers,
Angel & The JigsawStack Team

As the holiday season fills the air with joy and wonder, we’re reflecting on an incredible 2024. This year has been a whirlwind of innovation, growth, and milestones, and we’re so grateful for our amazing community, which has supported us every step of the way.

We’ve been working on some big things lately, and it’s time to share them with you. So, grab a cup of hot cocoa, and let’s dive into the updates that will set you up for an even brighter 2025!

What’s New

Enhanced Prompt Engine

Our Prompt Engine has received significant upgrades to make your workflows even smoother:

• Real-Time Streaming: Ideal for live applications.

• Pre-Optimized Templates: Faster setup with customizable options.

• Instant Web Data Access: Seamlessly integrate live information.

• Smarter, Cost-Effective Prompts: Reduce costs while optimizing performance.

Explore the full details in our blog: Prompt Engine: Internet, Streaming & More.

Bring Your Own URLs to Search API

You can now specify URLs for custom searches with our Search API, giving you even greater control over the results. Use cases include targeted website searches, company-specific content, or private repositories.

Here’s how it works:

• Endpoint: /v1/web/search

• Body: Add a byo_urls parameter with an array of URLs you want to search.

• Options: Configure safe search, spell-checking, and AI-powered overviews.

Learn more here: Search API Documentation.

Postman collection

Access all of JigsawStacks API in the Postman Collection, making it even easier to test and explore all APIs. This integration allows you to interact with all endpoints directly from Postman.

Llama 3.3 Integration

The Prompt Engine now supports the Llama 3.3 model, providing advanced capabilities! Try Prompt Engine today and ensure you never have to worry about selecting the best model for your needs again.

Learn more here: Llama 3.3 Now Available.

Documentation Updates

We’ve simplified access to our documentation—everything is now available at https://jigsawstack.com/docs. Bookmark it and dive into guides, API references, and more.

Multimodal Embedding Model Alpha

We launched a multimodal embedding model in Alpha last month and would love your feedback. Unlike traditional embedding models, ours supports:

• Multiple Modalities: Text, images, PDFs, and audio.

• Broad Language Support: Over 80 languages.

Help us test the model during Alpha and receive four months of free access post-launch. Contact Yoeven at yoeven@jigsawstack.com to participate. Learn more here.

Recent Blogs

Forecasting with AI: Learn how our Prediction API simplifies time-series forecasting without requiring data science expertise. Read the blog Forecasting with AI in Seconds.

Vision + OCR: Unlock insights from PDFs and images with our vOCR API. Discover how it works here.

Behind the Scenes

At JigsawStack, we recognize the pain points developers face with repetitive backend tasks. Current solutions often fall short in performance, accessibility, and developer experience.

We are committed to building highly specialized AI models to make your lives easier. We promise speed, reliability, and ease of integration into any backend.

Read more about our vision here: Why We’re Building JigsawStack.

Get Started Today

• Documentation: Find setup guides and API references here.

• Community: Join the conversation on Discord or Twitter.

• Alpha Testing: Sign up to test our multimodal embedding model by emailing yoeven@jigsawstack.com.

Wishing You a Wonderful Holiday Season! ✨

As we deck the halls and prepare for the New Year, we want to thank you for being part of our journey. Together, we’ve built something special, and we can’t wait to see what you will achieve in 2025.

Warm wishes and happy building,
Angel & The JigsawStack Team

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

It’s that spooky time of year, and while the Halloween spirit is in full swing, we’ve been brewing up some exciting updates at JigsawStack!

From new tools to streamlined APIs, our goal is to make developing AI applications as seamless and powerful as possible. Plus, Yoeven just completed the Funding London program, giving JigsawStack wider access to the UK and Europe markets.

Depreciation notice 👇

First, some housekeeping! To ensure we’re delivering the best AI-focused tools, we’ve deprecated several APIs that no longer align with our goals, including the geo APIs (city, country, state, distance, timezone, and geohash) and the email validation API. This allows us to focus on what matters most: innovative AI capabilities.

Investor & Developer Events in London: Yoeven attended back-to-back meetings with developers & startups in London, continuing to receive feedback that drives JigsawStack forward. We’re also hosting a cozy hackathon on the 9th of November in London.

New Article Spotlight: Scaling DevTools is a great read for anyone starting a new product or side project, talks about different ways to quickly validate your idea and how to scale!

Next.js Conf '24 Highlights: I had an amazing time at Next.js Conf '24, where I connected with developers, Vercel, and Supabase teams and explored exciting new trends in generative UI and LLMs as APIs. Shoutout to Oleg Akbarov for his inspiring talk on these topics—right in line with what we’re building at JigsawStack!

One feature I’m especially excited about is Turbopack, now stable in Next.js 5. With its incredible speed improvements, like up to 76% faster server startup and nearly 100% faster code updates, Turbopack is going to make our local development and iteration process much smoother. This means faster project launches and updates, allowing us to deliver even better developer experiences with JigsawStack’s AI tools.

Here’s the latest from JigsawStack—let’s dive in!

What’s New

We are Launching an Embedding Service in Alpha!
As part of our AI SDK, we’re introducing a new embedding service focused on filling the gaps left by existing models like those from OpenAI and Cohere.

Many current embedding models are limited to text and often lack multilingual support, especially in RAG applications. Our Alpha launch aims to offer a multimodal embedding for images, PDFs, and other document types with over 80+ languages supported.

We’re market testing this with both current and new users to refine the value proposition and quality. Learn more about the model here. Reach out to Yoeven on X or drop him an email at yoeven@jigsawstack.com with your use case for access.

We’re offering the API for free during Alpha and up to four months post-launch in production for companies needing a powerful, adaptable embedding solution.

Updated Documentation with Language Support. Navigating JigsawStack just got easier! The documentation now includes a full list of supported languages across the APIs, making it simple to find the language support you need for translation, speech-to-text, and more.

• AI in Supabase Series: We’re launching a short video series to help you leverage AI directly within your Supabase dashboard. Our first video is live! Learn how to automatically translate user-generated content using Postgres functions and the HTTP extension. Check it out here.

• JigsawStack Next.js Starter Kit: We’ve created a Next.js Starter Kit for you! This template integrates JigsawStack’s AI SDK to help you set up projects with tools like VOCR, Sentiment Analysis, Translation, and Text-to-Speech. Clone it here to get started in no time.

• vOCR Demo is Live: We’re thrilled to unveil a new demo showcasing the Vision OCR API in action. Powered by our advanced vLLMs and OCR models, this tool extracts data from documents with ultra-high accuracy. Watch the demo here to see it in action!

• Prompt Engine Templates: Introducing the Prompt Engine Templates! This gallery of optimized prompt templates lets you select and execute predefined prompts with JigsawStack’s Prompt Engine. We also invite you to contribute your Prompt for the community through our discord!

Why This Matters

These updates are all about refining your AI development experience, providing you with faster, more accurate tools, and making integration as seamless as possible. With each release, we’re simplifying AI workflows so you can focus on building and innovating.

Get Started Today

Ready to dive into the latest tools? Head to our documentation for setup instructions, or join us on Discord and Twitter to connect with our community. We’re excited to see what you’ll create with JigsawStack!

Let’s Get Connected

We’d love to hear from you and discuss how JigsawStack can support your AI development needs. Whether you have questions, feedback, or ideas, let’s set up a time to chat! Book a 15-minute meeting with me here.

Happy Halloween, and thanks for being part of the journey!

Cheers,
Angel & The JigsawStack Team 🎃

Hope you’re doing well! October has been action-packed here at JigsawStack, with a mix of exciting development news, investor meetings, and even a quick visit with family.

Yoeven, was on a jam-packed tour across France and London, diving deep into investor conversations and back-to-back developer events. Despite the full schedule, he managed to spend quality time with his mom, who was in town for a visit—a reminder that family moments are just as important as those milestone meetings!

Earlier in the month, I was part of Tech Week in both San Francisco and Los Angeles. In SF, I joined a three-day hackathon at Horizon SF, alongside 100+ brilliant developers, sharing creative ideas and building together with a stunning city view, many thanks to the Founder Inc team.

In LA, I had the pleasure of connecting with other innovators at an incredible Mix & Mingle, thanks to Owen Carew. The energy and ideas exchanged here were inspiring. Overall I can’t wait for the next Tech Week!

We are also thrilled to announce that JigsawStack has secured $500,000 in pre-seed funding, lead by Antler and amazing group of visionary investors! This funding is a big step toward our goal of helping developers everywhere streamline complex backend tasks with AI integrated effortlessly.

Read more about it or check out our post

And now, here’s what’s new on JigsawStack!

• Line-by-Line Sentiment Analysis: Our Sentiment API now offers line-by-line sentiment tracking, ideal for capturing nuanced emotional shifts in long texts such as customer reviews, emails, and support tickets. This helps you pinpoint key areas in conversations, ensuring targeted and insightful responses.

• ARES Partnership: We’re excited to share that GetARES.ai has integrated JigsawStack’s AI Search into its platform! ARES users now have access to our search capabilities, which are ideal for real-time research and creative problem-solving.

• Upgraded Speech-to-Text Model: We’ve upgraded our open source insanely-fast-whisper from Whisper 3 Large to Whisper 3 Large Turbo adding speed gains to an already blazing fast transcription model, the biggest speed gain is especially noticeable when using speaker splitting.

• LangChain.js Integration: JigsawStack is now accessible through LangChain.js, allowing you to leverage tools like AI Scraping, Prompt Engine, and Speech-to-Text in your LangChain projects, making way more streamlines to integrate multiple AI features.

• Enhanced AI Scraper: The AI Scraper now automatically maps data to user defined keys, saving you the time and hassle of cleaning up scraped data, allowing for your scraping workflows to be more efficient.

• Improved AI Search: We’ve migrated our AI Search overview feature to Groq’s LLMs, ensuring a faster search experience with fallback LLMs for larger context size.

• Landing page demo: You can now try any of JigsawStack services live on the individual API landing page without writing code. My favorites are Text to Speech and vOCR! You can share it with your no-code friends as they can use them as micro tools their projects!

Why This Matters

These updates are all about making your development experience faster, more precise, and easier. Whether you’re automating workflows, building with advanced AI, or starting a new project, JigsawStack goal is to provide a single AI SDK to elevate your backend work!

Get Started Today

Ready to dive in? Check out our documentation for quick setup instructions, or join us on Discord and Twitter to connect with the JigsawStack community. We’d love to see what you’re building and hear your feedback on these new features!

Thank you for being part of JigsawStack’s journey—we’re excited to keep building amazing things together.

Cheers,
Angel & The JigsawStack Team

Hope you’re doing well! We’ve been hard at work over here at JigsawStack, and we’ve got some awesome updates to share that are going to make working with AI even easier and more powerful for you.

First off, some big news—our CEO and Founder, Yoeven, is in London right now participating in the Investment Readiness Program for diverse founders. This program helps companies like ours get ready to raise external capital, and we’re thrilled to have Yoeven in this program, driving JigsawStack forward.

And on my end, I’m super excited to introduce myself—I'm Angel Pichardo, the new Founding Developer Relations Lead here at JigsawStack. I’m thrilled to be part of this team and to help YOU build amazing things with our AI tools. My mission is to make sure everything we do helps you, the developer, have the best experience possible.

What's New:

Groq x JigsawStack Partnership

• Prompt Engine Powered by Groq: Our Prompt Engine is now turbocharged with Groq’s LPU Inference Engine, delivering rapid results for your AI applications, ensuring fast and seamless performance. No need to worry about rate limits or API keys—our subscription model has you covered!

• Text-to-Speech API: We’ve significantly improved our text-to-speech capabilities. Get hyper-realistic speech in over 100 languages and accents, with less than 200ms latency and voice cloning support.

• Search API: We’ve launched a new AI Search API, offering Perplexity-like AI overviews and high-performance search built for AI accuracy.

Prompt Engine: Auto-pick the best LLM on every prompt!

• Mixture-of-Agents (MoA) Update: Our MoA in the Prompt Engine automatically picks the top LLMs for your task, combining outputs for higher quality and faster results. No need to switch models—MoA optimizes everything for you!

• NSFW Detection: Our NSFW API was voted #1 by users among NSFW APIs in detecting explicit content! Improve your app’s safety and streamline your workflow with our fast and cost-effective solution.

• New SDKs: We’ve added support for JavaScript and Python SDKs, making it easier to access all of JigsawStack’s APIs with just a few lines of code, including Window.ai integration for specific frontend use cases.

• Security Enhancements: You can now disable logs for added privacy and update our Text-to-SQL API to pass a schema and directly query databases with natural language.

Why This Matters:

We’ve made these updates with you in mind—so your applications can run faster, smarter, and more securely, helping you build the best solutions possible.

Getting Started:

Ready to dive in? Check out our updated documentation here to see all the new features in action.

We’d Love to Hear From You!

Your feedback is very important to us, and it helps us improve. Have any thoughts or questions about the new updates? Let us know here.

And don’t forget to join our community on Discord and Twitter. We’re all about collaboration and would love to see what you’re working on!

Thanks for being a part of JigsawStack. We can’t wait to see what you’ll create with these new tools!

Cheers,
Angel & The JigsawStack Team