needle social preview
tts-stt14,086Apache 2.0

needle

Automation foundation model for tiny devices: 2-bit, 8-29 MB, tool calls, ASR, structured extraction and embeddings on phones, wearables, smart homes, robots,…

Updated Oct 19, 2026
Website GitHub
Platforms
docker, web
Pricing
free-open-source
Status
active
License
Apache 2.0

What it does

Core capabilities at a glance

  • Cactus
  • Edge AI
  • Foundation Model
  • Function Calling
  • ON Device AI
  • Tinyml
  • Tool Calling

Deep dive

The full breakdown - performance, comparisons, and setup

needle

needle is a speech (TTS/STT) tool - Automation foundation model for tiny devices: 2-bit, 8-29 MB, tool calls, ASR, structured extraction and embeddings on phones, wearables, smart homes, robots, cars and microcontrollers.

Overview

A foundation model for mobiles, wearables, robots, smart home, automotive and microcontrollers. The whole model is a single 8-29 MB binary built on our Simple Attention Network, and we trade general chat capacity to beat models 10x its size on mobile tool calls and match 2-3x bigger models on extraction.

  • Tool calls: given the functions your app exposes, Needle picks the right ones and fills every argument from what the user said. Ask for two things and you get two calls in order; ask for something no tool covers and you get an empty list, not a guess. - Structured extraction: declare a shape, hand over messy text, get typed fields back: an invoice, a booking, a notification, a form. The decode grammar guarantees the output parses, and extraction generalises to classification. - Text embedding: the same model returns a vector for a sentence, so an app can search, match and route locally. - Speech: Whistle, our speech-to-text model, shares Needle's container and engine. One build gives Needle audio input: the clip goes in, the tool calls come out.

needle is open-source, written primarily in Python, with 14,086 GitHub stars under the Apache 2.0 license. It was last updated on 2026-10-18.

Key capabilities

From the project's documentation:

  • Text embedding: the same model returns a vector for a sentence, so an app can search, match and route locally.

Install

A quick way to get started (always check the official docs for the latest):

pip install cactus-needle

How it fits a local-AI stack

needle runs on your own hardware, so pair it with a model and a GPU sized to your needs. Use the VRAM calculator to pick a model that fits your card, and see what you can run for hardware guidance. Related speech (TTS/STT) tools in the directory:

Sources

Stats from GitHub, 2026-10-19.

Frequently asked

Quick answers to common questions

What is needle?

needle is a tts-stt tool for local AI workloads. Automation foundation model for tiny devices: 2-bit, 8-29 MB, tool calls, ASR, structured extraction and embeddings on phones, wearables, smart homes, robots,…

Is needle free and open source?

Yes, needle has 14,086 GitHub stars and is licensed under Apache 2.0. You can self-host it for free on docker, web.

What platforms does needle support?

needle runs on docker, web.

What hardware do I need for needle?

The hardware requirements depend on which models you run. Check our hardware directory for compatible GPUs and systems. needle has 14,086 GitHub stars and an active community.

Does needle support GPU acceleration?

needle's GPU support depends on your specific setup. Check the documentation for details. For the best performance, pair it with an NVIDIA RTX 4090 or 5090.

What are the best alternatives to needle?

Popular alternatives include other tts-stt tools in our directory. Browse our full collection at /tool for comparisons, community reviews, and benchmark data to find the right fit for your workflow.

How much does needle cost?

needle is free-open-source. It is completely free and open source to self-host.

Pairs well with

Complementary tools, models, and hardware