AI
Data — Language, speech and reasoning APIs
One OpenAI-compatible API for chat, vision, OCR, transcription, speech synthesis, translation and retrieval — running on dedicated hardware, with models hosted in the service itself.
- Rok
- 2026
- Kategória
- AI
Product
One API for every language task
Chat, vision, OCR, transcription, speech synthesis, translation and retrieval — behind one standard interface. The models run locally, on dedicated hardware.
What you get
An OpenAI-compatible API
Chat, streaming, structured output, function calling, vision and embeddings — with a developer console, API keys and docs in Persian, English, Spanish and Arabic.
Speech synthesis
Persian plus 23 more languages, with five male and five female synthetic voices per language. Each voice is stable and repeatable, and long text is split and read without breaks.
Transcription
Tuned for spontaneous Persian speech, with automatic language detection, a file mode and a live streaming mode that returns text while the speaker is still talking.
A dedicated legal model
A legal model with retrieval (RAG), alongside a general one.
Built-in tools
OCR, PDF, file search, a code sandbox and MCP.
Under the hood
What it is built from
Data is built in layers. At the edge, Caddy handles HTTPS and rate limiting, and behind it a LiteLLM gateway serves the OpenAI-compatible interface, with API keys, per-model access and spend tracking. The service itself is written in Python with FastAPI and Uvicorn, and live transcription is streamed over WebSocket.
The models run on a dedicated NVIDIA Blackwell GPU with 96 GB of memory: quantised language models through llama.cpp, the rest on PyTorch 2 with CUDA 12.8 and Hugging Face Transformers. Speech synthesis with a neural audio codec, fine-tuned for Persian with LoRA, produces the voices, and librosa, SciPy and FFmpeg handle the audio work.
Documents go through two independent OCR engines, Tesseract and EasyOCR, whose results are settled by consensus voting, with PyMuPDF reading PDFs. Retrieval combines BM25 with embeddings, and web search runs through SearXNG. Data lives in PostgreSQL, cached responses in Redis and local indexes in SQLite, with Docker and systemd keeping the service running.
See the Data console
The service is live. The developer console, API keys and docs are there.
From the same team
An intelligent legal assistant for lawyers and law offices.
Postavené na
- LiteLLM
- Caddy
- Python
- FastAPI
- Uvicorn
- WebSocket
- llama.cpp
- PyTorch
- CUDA
- Hugging Face
- NVIDIA
- librosa
- SciPy
- FFmpeg
- Tesseract
- EasyOCR
- PyMuPDF
- SearXNG
- PostgreSQL
- Redis
- SQLite
- Docker
- systemd
Ďalšie práce
Máte čo stavať?
Povedzte nám, na čom pracujete. Úprimne vám povieme, či sme na to ten správny tím.
alebo nám napíšte na hello@larsima.com