Viewing profile — apichar
apichar
HN member- Joined
- Fri, Sep 27, 2024, 6:29 PM UTC
- HN karma
- 14
- Public activity
- 22 items
- HN profile
- View on Hacker News ↗
About apichar
No profile information was provided.
Recent public activity
- story
- story
- story
- story
-
comment
Comment #43438030
We encourage everyone to try out our model. Here is a link to get started: https://jigsawstack.com/speech-to-text
-
story
Show HN: We are 2.4x faster than Open AI latest SST model
Speech-to-Text technology is crucial for audio processing applications, but most solutions are limited by speed, accuracy, or feature constraints. What if you could transcribe audi…
-
story
Show HN: We're Leveraging DeepSeek R1 for AI Fine-Tuning and Synthetic Data
LLMs are evolving fast—DeepSeek R1 is one of the latest making waves. But beyond the hype, how can it actually improve AI applications? At JigsawStack, we’re testing how DeepSeek R…
-
story
Show HN: Open-Source MCP Server for Context and AI Tools
Large Language Models (LLMs) are powerful, but they’re limited by fixed context windows and outdated knowledge. What if your AI could access live search, structured data extraction…
-
comment
Comment #43295672
You can upload a PDF directly, and the vOCR API supports a page_range parameter so you can specify which pages to process in a single request (e.g., [1,10]). If your PDF has more t…
-
comment
Comment #43294412
True- I saw that too, but I also wanted to start a thread to chat with the community and hear different perspectives. Would love to get your thoughts!
-
comment
Comment #43294319
Our pricing model is being updated soon to be even more cost-effective. Currently, we support up to 10 pages per API request. With the upcoming token-based pricing, costs will drop…
-
story
We outperformed Mistral OCR with a tiny team
Mistral recently launched their OCR model, claiming to be the best in the world. We put that claim to the test against JigsawStack vOCR — our own OCR solution, built by a team of j…
-
story
Show HN: AI-Powered Web Scraper – No Selectors, No Headaches
We just launched a demo of JigsawStack’s AI WebScraper, and it makes web scraping effortless. Instead of manually inspecting HTML and dealing with bot blockers, just describe the d…
-
story
Can AI Accurately Translate Text in Images While Keeping the Original Style?
We’re working on an Image-to-Image Translation Model that extracts, translates, and reinserts text into images while keeping the original style. So far, our pipeline involves: - OC…
- story
- story
-
story
JigsawStacks Prompt Engine's Input Limit Increased from 30k to 500k Characters
We're excited to announce JigsawStack's Prompt Engine total input limit has been increased from 30,000 characters to a 500,000 characters! No matter how you use Prompt Engine—be it…
-
story
We built the fastest Speech-To-Text AI API!
We conducted an in-depth analysis of four leading speech-to-text providers—JigsawStack, Groq, AssemblyAI, and OpenAI—focusing on latency, accuracy, cost, and features. Key findings…
- story
-
comment
Comment #41941205
We're thrilled to announce that JigsawStack’s AI tools are now available in LangChain.js! Automate tasks like web scraping, transcription, and SQL generation with just a few lines …
- story
- story