Skip to main content
ToolPotion
AI Advisor
Submit a Tool (Free)

NeuDecide

No ratings yet
AI ModelsAI Models & LLMsOpen Source · Web

NeuDecide is a compact voice-action model that converts speech directly into function calls. It operates offline, requires no GPU, and adapts to various tools through JSON schemas.

View Model
Share
View Model
Share

Description

NeuDecide is a voice-action model designed to convert spoken commands directly into function calls without the need for transcription. This model is particularly compact, with a size of 43 MB, and can run efficiently on a single thread using ONNX Runtime. It does not require a GPU or an internet connection once downloaded, making it highly accessible for various applications.

Read More

The model operates by taking audio input and a list of tools, outputting the appropriate tool call based on the input. Tools are defined using JSON schemas, allowing users to modify the model's capabilities by simply altering the JSON, rather than retraining the model. This flexibility makes NeuDecide suitable for a wide range of applications, from controlling smart home devices to executing specific software functions.

NeuDecide's architecture includes a pre-trained streaming English speech encoder and a tool-calling encoder-decoder, initialized from Needle and trained as a unified system. The inference process involves three ONNX graphs: the audio encoder, tool encoder, and decoder step, each contributing to the model's ability to process and respond to audio commands effectively.

Despite its capabilities, NeuDecide has some limitations. It can trigger on noise, lacks a calibrated confidence score, and is limited to English. Additionally, it is recommended to keep tool lists short to optimize performance. The model is best used alongside a larger model for handling more complex or open-ended tasks.

NeuDecide is open-source, licensed under Apache 2.0, and can be integrated into various systems with Python 3.10 to 3.13. It is ideal for developers looking to implement voice-action capabilities in their applications without extensive computational resources.

  • CategoryAI Models & LLMs
  • Pricing ModelOpen Source
  • DeploymentRuns locally
  • PlatformsWeb

NeuDecide Highlights

  • Converts speech to function calls

  • Operates offline without GPU

  • Uses JSON schemas for tool definitions

  • Compact size of 43 MB

  • Runs on ONNX Runtime

  • Pre-trained English speech encoder

  • Tool-calling encoder-decoder

  • Open-source under Apache 2.0

Getting Started with NeuDecide

  1. Access model: Visit Hugging Face repository

  2. Authenticate: Agree to terms and conditions

  3. Set up environment: Install Python 3.10–3.13

  4. Integrate via API: Use JSON schemas for tools

  5. Optimise: Test with various audio inputs

NeuDecide's Use Cases

  • Smart Home Control
  • Software Automation
  • Voice-Activated Tools
  • Offline Voice Processing
  • Custom Tool Integration

FAQ from NeuDecide

NeuDecide Reviews

NeuDecide Reviews

Loading...

Popular AI Tools Like NeuDecide

Bark AI Model

AI Models

Bark is a transformer-based text-to-audio model by Suno, capable of generating realistic multilingual speech and other audio forms. It supports research with pretrained model…

AI Models & LLMs
View Tool

Bark AI Model

AI Models

Transformer-based text-to-audio model by Suno, capable of generating realistic multilingual speech and other audio forms. It supports research with pretrained model…Bark is a transformer-based text-to-audio model by Suno, capable of generating realistic multilingual speech and other audio forms. It supports research with pretrained model…

AI Models & LLMs
See the Top 5 AI Models

Sesame CSM — Speech Generation Model

AI Models

Sesame CSM is a conversational speech model that generates audio codes from text and audio inputs. It utilizes a Llama backbone and is designed for research and educational…

AI Models & LLMs
View Tool

Sesame CSM — Speech Generation Model

AI Models

Conversational speech model that generates audio codes from text and audio inputs. It utilizes a Llama backbone and is designed for research and educational…Sesame CSM is a conversational speech model that generates audio codes from text and audio inputs. It utilizes a Llama backbone and is designed for research and educational…

FeaturedAI Models & LLMs
See the Top 5 AI Models

Inkling Model Card - Thinking Machines Lab

AI Models

975B-parameter multimodal AI model designed for developers. It accepts text, image, and audio inputs, generating text outputs for various applications, including…Inkling is a 975B-parameter multimodal AI model designed for developers. It accepts text, image, and audio inputs, generating text outputs for various applications, including…

FeaturedAI Models & LLMs
See the Top 5 AI Models

OpenAI Whisper Model

AI Models

OpenAI Whisper is a pre-trained model for automatic speech recognition and translation. It supports multiple languages and is designed to generalize across datasets without…

AI Models & LLMs
View Tool

OpenAI Whisper Model

AI Models

Pre-trained model for automatic speech recognition and translation. It supports multiple languages and is designed to generalize across datasets without…OpenAI Whisper is a pre-trained model for automatic speech recognition and translation. It supports multiple languages and is designed to generalize across datasets without…

AI Models & LLMs
See the Top 5 AI Models

NVIDIA NemotronLabs VoiceChat

AI Models

NVIDIA NemotronLabs VoiceChat is a real-time, full-duplex speech model for conversational AI. It integrates speech understanding and generation in one architecture, reducing…

AI Models & LLMs
View Tool

NVIDIA NemotronLabs VoiceChat

AI Models

Real-time, full-duplex speech model for conversational AI. It integrates speech understanding and generation in one architecture, reducing…NVIDIA NemotronLabs VoiceChat is a real-time, full-duplex speech model for conversational AI. It integrates speech understanding and generation in one architecture, reducing…

AI Models & LLMs
See the Top 5 AI Models

gemma-3n-E4B-it Model

AI Models

Gemma-3n-E4B-it is a lightweight, state-of-the-art AI model from Google, designed for efficient execution on low-resource devices. It supports multimodal input, handling text,…

AI Models & LLMs
View Tool

gemma-3n-E4B-it Model

AI Models

Lightweight, state-of-the-art AI model from Google, designed for efficient execution on low-resource devices. It supports multimodal input, handling text,…Gemma-3n-E4B-it is a lightweight, state-of-the-art AI model from Google, designed for efficient execution on low-resource devices. It supports multimodal input, handling text,…

AI Models & LLMs
See the Top 5 AI Models

Dia-1.6B AI Model

AI Models

Dia-1.6B is a text-to-speech model by Nari Labs, featuring 1.6 billion parameters. It generates realistic dialogue from transcripts, supporting emotion and tone control, and can…

Text to Speech
View Tool

Dia-1.6B AI Model

AI Models

Text-to-speech model by Nari Labs, featuring 1.6 billion parameters. It generates realistic dialogue from transcripts, supporting emotion and tone control, and can…Dia-1.6B is a text-to-speech model by Nari Labs, featuring 1.6 billion parameters. It generates realistic dialogue from transcripts, supporting emotion and tone control, and can…

Text to Speech
See the Top 5 AI Models

Gemma 3n Model

AI Models

Gemma 3n is a family of lightweight, open-source AI models by Google, designed for efficient execution on low-resource devices. It supports multimodal inputs, including text,…

AI Models & LLMs
View Tool

Gemma 3n Model

AI Models

Family of lightweight, open-source AI models by Google, designed for efficient execution on low-resource devices. It supports multimodal inputs, including text,…Gemma 3n is a family of lightweight, open-source AI models by Google, designed for efficient execution on low-resource devices. It supports multimodal inputs, including text,…

AI Models & LLMs
See the Top 5 AI Models
1 of 8