Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
Blueprints

Blueprints is a Mozilla AI initiative helping developers get started with building open-source
AI solutions.

All Blueprints
Text Link
February 18, 2025
Fine-tune a speech recognition model for your voice

This Blueprint demonstrates how to fine-tune a Speech-To-Text model in your own language using CommonVoice data and your own voice data. Check the audio preview of a model fine-tuned on the Galician set Common Voice 17.0.

Text Link
January 17, 2025
Create your own tailored podcast using your documents

This blueprint demonstrates how you can use open-source models & tools to convert input documents into a podcast featuring two speakers.

Tools

Trusted open-source tools to assist you in building AI solutions.

All Tools
Text Link
December 12, 2024
OuteTTS

OuteTTS is an package for using OuteTTS text-to-speech models.

Text Link
December 3, 2024
Streamlit

Streamlit is an open-source Python framework for creating interactive data applications effortlessly.

Text Link
October 7, 2024
Gradio

Gradio allows you to build a friendly web interface so that anyone can use your project.

Text Link
October 7, 2024
HuggingFace Hub

The huggingface_hub library is used to interact with the HuggingFace Hub, enabling you to discover pre-trained models and datasets for your projects.

Datasets

Vetted open-source datasets to assist you in building AI solutions.

All Datasets
Text Link
October 30, 2024
Common Voice

A multilingual, crowdsourced collection of voice recordings from Mozilla.

Models

Recommended open-source datasets to assist you in building AI solutions.

All Models
Text Link
December 12, 2024
OuteTTS-0.1-350M

OuteTTS-0.1-350M is a novel text-to-speech synthesis model.

Text Link
Qwen2.5-3B-Instruct-GGUF

Qwen2.5-3B-Instruct-GGUF is an instruction-tuned model that generates long-form content, and is optimized for efficient deployment via the GGUF format.

Content

The latest open-source content related to Blueprints, Tools, Datasets and Models.

All Content
Text Link
Comparing RAG, Long-Context Models, and Lightweight Alternatives

Articles that played a key-role in shaping the ideas and approaches behind this Blueprint.

Mozilla.ai
Text Link
Confidently Build with Open-Source AI

Mozilla.ai Blueprints are customizable workflows for building AI applications using open-source tools and models.

Mozilla.ai
No results found.
Please try another filter combination.
Blueprints

Blueprints are a Mozilla AI initiative helping developers get started with building open-source AI solutions.

Explore All Blueprints
Text Link
February 18, 2025
blueprint
Speech
Document
Fine-tune a speech recognition model for your voice

This Blueprint demonstrates how to fine-tune a Speech-To-Text model in your own language using CommonVoice data and your own voice data. Check the audio preview of a model fine-tuned on the Galician set Common Voice 17.0.

Text Link
January 17, 2025
blueprint
Document
Podcast
Create your own tailored podcast using your documents

This blueprint demonstrates how you can use open-source models & tools to convert input documents into a podcast featuring two speakers.

Text Link
January 16, 2025
blueprint
Document
Q&A
Query structured documents using a lightweight LLM workflow

This Blueprint demonstrates how to use open-source models and a simple LLM workflow to answer questions based on structured documents.

Text Link
blueprint
CompVis
Map Features
Map Features in OpenStreetMap with Computer Vision

This Blueprint shows you how to fine-tune an object detection model to map features in OpenStreetMap.

Tools

Trusted open-source tools to assist you in building AI solutions.

Explore All Tools
Text Link
December 12, 2024
tool
OuteTTS

OuteTTS is an package for using OuteTTS text-to-speech models.

Text Link
December 3, 2024
tool
Streamlit

Streamlit is an open-source Python framework for creating interactive data applications effortlessly.

Text Link
October 7, 2024
tool
Gradio

Gradio allows you to build a friendly web interface so that anyone can use your project.

Text Link
October 7, 2024
tool
HuggingFace Hub

The huggingface_hub library is used to interact with the HuggingFace Hub, enabling you to discover pre-trained models and datasets for your projects.

Text Link
October 7, 2024
tool
HuggingFace Transformers

HuggingFace Transformers provides thousands of pretrained models to perform tasks on different modalities such as text, vision, and audio.

Text Link
September 24, 2024
tool
Flower

Flower is a customizable, extendable, and framework-agnostic framework for building federated learning systems.

Text Link
tool
SAM 2

The Segment Anything Model 2 (SAM 2) is an advanced AI model developed by Meta AI, designed to perform real-time, promptable object segmentation in both images and videos.

Text Link
tool
Ultralytics

Ultralytics provides cutting-edge computer vision models, including YOLO11, enabling developers to integrate real-time object detection, segmentation, and classification into AI applications with minimal effort.

Text Link
tool
PyMuPDF

PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.

Text Link
tool
Llama.cpp

Enable LLM inference with minimal setup and state-of-the-art performance on a wide range of hardware

Datasets

Vetted open-source datasets to assist you in building AI solutions.

Explore All Datasets
Text Link
October 30, 2024
dataset
Common Voice

A multilingual, crowdsourced collection of voice recordings from Mozilla.

Models

Recommended open-source models to assist you in building AI solutions.

Explore All Models
Text Link
December 12, 2024
model
OuteTTS-0.1-350M

OuteTTS-0.1-350M is a novel text-to-speech synthesis model.

Text Link
model
Qwen2.5-3B-Instruct-GGUF

Qwen2.5-3B-Instruct-GGUF is an instruction-tuned model that generates long-form content, and is optimized for efficient deployment via the GGUF format.

Content

The latest open-source content related to Blueprints, Tools, Datasets and Models.

Explore All Resources
Text Link
content
resource
Comparing RAG, Long-Context Models, and Lightweight Alternatives

Articles that played a key-role in shaping the ideas and approaches behind this Blueprint.

Mozilla.ai
Text Link
content
resource
Confidently Build with Open-Source AI

Mozilla.ai Blueprints are customizable workflows for building AI applications using open-source tools and models.

Mozilla.ai
Text Link
content
resource
Methodologies to leverage LLMs for Document Q&A

Advantages and trade-offs of various approaches that utilize LLMs for document querying.

Mozilla.ai
Text Link
content
resource
Other Open Source Alternatives

Explore existing OSS to create podcasts.

Mozilla.ai
Text Link
content
resource
Practical use cases to create podcasts

Turn notes or newsletters into audios.

Mozilla.ai
Text Link
content
resource
Practical use cases to quickly retrieve information from your documents

Quickly access information on your collection of documents stored on your computer.

Mozilla.ai
Text Link
content
resource
STT models for real-world applications

Make AI inclusive and accessible.

Mozilla.ai
Text Link
content
resource
Try these prompts for a fun podcast

Draw inspiration from unique personalities.

Mozilla.ai
Text Link
Federated AI
tags
Text Link
Image Segmentation
tags
Text Link
Object Detection
tags
Text Link
Automatic Speech Recognition
tags
Text Link
Speech-to-Text
tags
Text Link
Query structured documents Q&A
tags
Text Link
Emails
tags
Text Link
Newsletter
tags
Text Link
Podcast
tags
Text Link
Community
tags
Text Link
Events
tags
Text Link
Discord
tags
Text Link
Data Extraction
tags
Text Link
User-Interface
tags
Text Link
Performance Optimization
tags
Text Link
LLM Inference
tags
Text Link
Language Modelling
tags
Text Link
Text-to-Text
tags
Text Link
Text-to-Speech
tags
Text Link
LLM
tags
Text Link
Email
tags
Text Link
Podcast personalities
tags
Text Link
Document-to-podcast
tags
Text Link
Blueprints
tags
Text Link
Use Cases
tags
Text Link
English
tags
Text Link
General Language
tags
Text Link
Multilingual
tags
Text Link
Audio
tags
Text Link
Text
tags
Text Link
Finetuning
tags
Text Link
Local AI
tags
Text Link
Federated Learning
tags
Text Link
LLM Integration
tags
This is some text inside of a div block.
Text Link
Algorithm
Text Link
Document
Text Link
Speech
Text Link
Federated AI
Text Link
CompVis
Text Link
Podcast
Text Link
Document
Text Link
Map Features