Resemble AI ORG

A python package to analyze and compare voices with deep learning

AI powered speech denoising and enhancement

WIP: Open Source Implementation of "MelNet: A Generative Model for Audio in the Frequency Domain"

Resemble's voice cloning engine within Unity

SoTA open-source TTS

Open Audio Watermarking Tool

super expressive prompting model based on ltx2.3

Monotonic Alignment Search

This is sample code for an Alexa skill that uses realistic voice cloning powered by Resemble AI's text-to-speech API, and Open AI’s GPT-3 AI engine.

[ICASSP 2025] "FLowHigh: Towards efficient and high-quality audio super-resolution with single-step flow matching"

No description.

Simple text to phonemes converter for multiple languages

No description.

No description.

resemble.ai API SDK

Agent skill for deepfake detection & media safety — detect AI-generated audio, images, and video with Resemble AI

NeMo: a toolkit for conversational AI

A module for normalising text.

Build real-time multimodal AI applications 🤖🎙️📹

No description.

An open-source Python library for audio time-scale modification.

Unsupervised Language Modeling at scale for robust sentiment classification

This utility allows one to cut multiple clips from a single or multiple audio files.

No description.

No description.

Chatterbox-Flash: Extending Chatterbox with Block Diffusion for Fast Speech Generation

Benchmark Arabic text diacritization dataset

eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.

Deep Learning Examples

Build realtime multimodal AI agents with Node.js

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Run OpenAI Whisper as a Cog model

GitHub Action to run kubectl

No description.

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Supplementary materials of Synthesizing Personalized Non-speech Vocalization from Discrete Speech Representations

Robust Speech Recognition via Large-Scale Weak Supervision

Github Action for executing Helm commands on EKS (using aws-iam-authenticator)

Official MCP server for Resemble AI — vibe code with instant API docs in your coding assistant (Cursor, Claude Code, etc.)

n8n community node for Resemble AI: deepfake detection, media intelligence, and invisible watermarking

Rivet plugin for Resemble AI deepfake detection, intelligence, and watermarking

Documentation for Resemble AI's Live VC websocket server

Resemble Examples — Quick start examples for the Resemble AI API in Python and JavaScript, with and without SDKs.

maximal update parametrization (µP)

Hackable and optimized Transformers building blocks, supporting a composable construction.

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

A python package for calculating the PESQ.

Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀

WebRTC and ORTC implementation for Python using asyncio

asyncio-based Interactive Connectivity Establishment (RFC 5245)

A Heroku buildpack for ffmpeg that always downloads the latest static build

Chinese Mandarin Grapheme-to-Phoneme Converter. 中文轉注音或拼音 (INTERSPEECH 2022)

Unofficial PyTorch Implementation of UnivNet Vocoder (https://arxiv.org/abs/2106.07889)

Automatically deploy your project to GitHub Pages using GitHub Actions. This action can be configured to push your production-ready code into any branch you'd like.

No description.