{"slug": "introducing-paxa-labs", "title": "Introducing Paxa Labs", "summary": "Paxa Labs, an AI research lab in Bangkok, has launched a suite of Thai-language AI models delivered through a single API, including text-to-speech, OCR, and translation. The models are designed to handle the unique challenges of Thai text, such as no spaces between words and mixed Thai-English usage. The lab also offers a credit-based billing system that charges before inference and refunds on failure.", "body_md": "Paxa Labs is an AI research lab in Bangkok. We build speech, translation, and document models for Thai and English, and ship them as one API.\n\nThai breaks the assumptions most language tooling is built on. Words are written without spaces, so something has to decide where one word ends and the next begins. Tone changes the word. Speakers move between Thai and English inside a sentence, with a product name and a number in the same breath. Business documents stack Thai and English text, tables, stamps, and handwriting on one page.\n\nGeneral-purpose models treat all of this as edge cases. For anyone building for Thai users, it is the input.\n\nSo we start from failures in real Thai speech, text, and documents. A failure becomes a data example and an evaluation. Repeated patterns shape the model, the training method, and the serving stack. The improved system goes back into the product, where the next difficult input tells us what to investigate next.\n\n**Text to speech.** Paxa Flash (`paxa-tts-flash-v1`\n\n) is our proprietary Thai speech model: 26 voices, including Isan, Northern, and Southern regional accents and English-first voices. MP3, Opus, or WAV, buffered or streamed, with optional word, sentence, or utterance timestamps. A WebSocket endpoint synthesizes as you send text, for agents and live captions. There is an OpenAI-compatible `/v1/audio/speech`\n\nalias, so an existing client works after a base URL change.\n\n**OCR.** `paxa-ocr-lite-v1`\n\nis our proprietary document model for PDF, PNG, JPEG, and WebP. Output is per-page Markdown or typed blocks (headings, paragraphs, lists, tables, figures). It is built for the documents Thai businesses actually handle: mixed scripts, stacked marks, stamps, and handwritten notes.\n\n**Translation.** `paxa-translation-lite-v1`\n\ntranslates fourteen source languages into Thai, with controls for formality, borrowed-word handling, a glossary, do-not-translate terms, and reference context. Markdown and HTML modes translate the prose and leave the markup in place, which matters in Thai: a tag moved by one character moves a word boundary.\n\n**Speech recognition** is still research. It ships when it survives real Thai audio.\n\nEvery product bills in credits, 1,000 credits to a dollar, pay as you go or on a monthly plan:\n\nEvery account starts with free credits. A request is charged before inference and refunded if inference fails, so a failed call never costs anything. We wrote up how that works and why it is the right order: [Charge before inference, refund on failure](https://paxalabs.com/blog/charge-before-inference).\n\n```\ncurl -X POST https://api.paxalabs.com/v1/tts \\\n  -H \"Authorization: Bearer $PAXA_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"text\": \"สวัสดีค่ะ ยินดีต้อนรับสู่ Paxa Labs\",\n    \"voice\": \"foithong\",\n    \"model\": \"paxa-tts-flash-v1\"\n  }' \\\n  --output speech.mp3\n```\n\nSign in with Google, GitHub, or Hugging Face, create a key, and the playground lets you try all three products in the browser before you write any code.\n\nEvery docs page at paxalabs.com/docs is also served as Markdown at its path plus .md. /llms.txt is the curated index, /llms-full.txt is the whole corpus, and an installable agent skill ships from the same source: npx skills add [https://paxalabs.com](https://paxalabs.com).\n\nThe lab's notebook covers the engineering behind the products, in English and Thai:\n\nWe will cross-post the next ones here. If you are building for Thai users and hitting something a general model gets wrong, we want to hear about it: [https://paxalabs.com/contact](https://paxalabs.com/contact).", "url": "https://wpnews.pro/news/introducing-paxa-labs", "canonical_source": "https://dev.to/paxalabs/introducing-paxa-labs-neo", "published_at": "2026-08-28 11:40:20+00:00", "updated_at": "2026-08-28 11:50:28.369717+00:00", "lang": "en", "topics": ["artificial-intelligence", "natural-language-processing", "ai-products", "ai-startups", "developer-tools"], "entities": ["Paxa Labs", "Paxa Flash", "paxa-tts-flash-v1", "paxa-ocr-lite-v1", "paxa-translation-lite-v1"], "alternates": {"html": "https://wpnews.pro/news/introducing-paxa-labs", "markdown": "https://wpnews.pro/news/introducing-paxa-labs.md", "text": "https://wpnews.pro/news/introducing-paxa-labs.txt", "jsonld": "https://wpnews.pro/news/introducing-paxa-labs.jsonld"}}