metavoice-src

Foundational model for human-like, expressive TTS

Stars: 3066

Visit

MetaVoice-1B is a 1.2B parameter base model trained on 100K hours of speech for TTS (text-to-speech). It has been built with the following priorities: * Emotional speech rhythm and tone in English. * Zero-shot cloning for American & British voices, with 30s reference audio. * Support for (cross-lingual) voice cloning with finetuning. * We have had success with as little as 1 minute training data for Indian speakers. * Synthesis of arbitrary length text

README:

MetaVoice-1B

MetaVoice-1B is a 1.2B parameter base model trained on 100K hours of speech for TTS (text-to-speech). It has been built with the following priorities:

Emotional speech rhythm and tone in English.
Zero-shot cloning for American & British voices, with 30s reference audio.
Support for (cross-lingual) voice cloning with finetuning.
- We have had success with as little as 1 minute training data for Indian speakers.
Synthesis of arbitrary length text

We’re releasing MetaVoice-1B under the Apache 2.0 license, it can be used without restrictions.

Quickstart - tl;dr

Web UI

docker-compose up -d ui && docker-compose ps && docker-compose logs -f

Server

# navigate to <URL>/docs for API definitions
docker-compose up -d server && docker-compose ps && docker-compose logs -f

Installation

Pre-requisites:

GPU VRAM >=12GB
Python >=3.10,<3.12
pipx (installation instructions)

Environment setup

# install ffmpeg
wget https://johnvansickle.com/ffmpeg/builds/ffmpeg-git-amd64-static.tar.xz
wget https://johnvansickle.com/ffmpeg/builds/ffmpeg-git-amd64-static.tar.xz.md5
md5sum -c ffmpeg-git-amd64-static.tar.xz.md5
tar xvf ffmpeg-git-amd64-static.tar.xz
sudo mv ffmpeg-git-*-static/ffprobe ffmpeg-git-*-static/ffmpeg /usr/local/bin/
rm -rf ffmpeg-git-*

# install rust if not installed (ensure you've restarted your terminal after installation)
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh

Using poetry (recommended)

# install poetry if not installed (ensure you've restarted your terminal after installation)
pipx install poetry

# disable any conda envs that might interfere with poetry's venv
conda deactivate

# if running from Linux, keyring backend can hang on `poetry install`. This prevents that.
export PYTHON_KEYRING_BACKEND=keyring.backends.fail.Keyring

# pip's dependency resolver will complain, this is temporary expected behaviour
# full inference & finetuning functionality will still be available
poetry install && poetry run pip install torch==2.2.1 torchaudio==2.2.1

Using pip/conda

NOTE 1: When raising issues, we'll ask you to try with poetry first. NOTE 2: All commands in this README use poetry by default, so you can just remove any poetry run.

pip install -r requirements.txt
pip install torch==2.2.1 torchaudio==2.2.1
pip install -e .

Usage

Download it and use it anywhere (including locally) with our reference implementation

# You can use `--quantisation_mode int4` or `--quantisation_mode int8` for experimental faster inference.  This will degrade the quality of the audio.
# Note: int8 is slower than bf16/fp16 for undebugged reasons. If you want fast, try int4 which is roughly 2x faster than bf16/fp16.
poetry run python -i fam/llm/fast_inference.py

# Run e.g. of API usage within the interactive python session
tts.synthesise(text="This is a demo of text to speech by MetaVoice-1B, an open-source foundational audio model.", spk_ref_path="assets/bria.mp3")

Note: The script takes 30-90s to startup (depending on hardware). This is because we torch.compile the model for fast inference.

On Ampere, Ada-Lovelace, and Hopper architecture GPUs, once compiled, the synthesise() API runs faster than real-time, with a Real-Time Factor (RTF) < 1.0.

Deploy it on any cloud (AWS/GCP/Azure), using our inference server or web UI

# You can use `--quantisation_mode int4` or `--quantisation_mode int8` for experimental faster inference. This will degrade the quality of the audio.
# Note: int8 is slower than bf16/fp16 for undebugged reasons. If you want fast, try int4 which is roughly 2x faster than bf16/fp16.

# navigate to <URL>/docs for API definitions
poetry run python serving.py

poetry run python app.py

Use it via Hugging Face
Google Colab Demo

Finetuning

We support finetuning the first stage LLM (see Architecture section).

In order to finetune, we expect a "|"-delimited CSV dataset of the following format:

audio_files|captions
./data/audio.wav|./data/caption.txt

Note that we don't perform any dataset overlap checks, so ensure that your train and val datasets are disjoint.

Try it out using our sample datasets via:

poetry run finetune --train ./datasets/sample_dataset.csv --val ./datasets/sample_val_dataset.csv

Once you've trained your model, you can use it for inference via:

poetry run python -i fam/llm/fast_inference.py --first_stage_path ./my-finetuned_model.pt

Configuration

In order to set hyperparameters such as learning rate, what to freeze, etc, you can edit the finetune_params.py file.

We've got a light & optional integration with W&B that can be enabled via setting wandb_log = True & by installing the appropriate dependencies.

poetry install -E observable

Upcoming

[x] Faster inference ⚡
[x] Fine-tuning code 📐
[ ] Synthesis of arbitrary length text

Architecture

We predict EnCodec tokens from text, and speaker information. This is then diffused up to the waveform level, with post-processing applied to clean up the audio.

We use a causal GPT to predict the first two hierarchies of EnCodec tokens. Text and audio are part of the LLM context. Speaker information is passed via conditioning at the token embedding layer. This speaker conditioning is obtained from a separately trained speaker verification network.
- The two hierarchies are predicted in a "flattened interleaved" manner, we predict the first token of the first hierarchy, then the first token of the second hierarchy, then the second token of the first hierarchy, and so on.
- We use condition-free sampling to boost the cloning capability of the model.
- The text is tokenised using a custom trained BPE tokeniser with 512 tokens.
- Note that we've skipped predicting semantic tokens as done in other works, as we found that this isn't strictly necessary.
We use a non-causal (encoder-style) transformer to predict the rest of the 6 hierarchies from the first two hierarchies. This is a super small model (~10Mn parameters), and has extensive zero-shot generalisation to most speakers we've tried. Since it's non-causal, we're also able to predict all the timesteps in parallel.
We use multi-band diffusion to generate waveforms from the EnCodec tokens. We noticed that the speech is clearer than using the original RVQ decoder or VOCOS. However, the diffusion at waveform level leaves some background artifacts which are quite unpleasant to the ear. We clean this up in the next step.
We use DeepFilterNet to clear up the artifacts introduced by the multi-band diffusion.

Optimizations

The model supports:

KV-caching via Flash Decoding
Batching (including texts of different lengths)

Contribute

See all active issues!

Acknowledgements

We are grateful to Together.ai for their 24/7 help in marshalling our cluster. We thank the teams of AWS, GCP & Hugging Face for support with their cloud platforms.

A Défossez et. al. for Encodec.
RS Roman et. al. for Multiband Diffusion.
@liusongxiang for speaker encoder implementation.
@karpathy for NanoGPT which our inference implementation is based on.
@Rikorose for DeepFilterNet.

Apologies in advance if we've missed anyone out. Please let us know if we have.

For Tasks:

Click tags to check more tools for each tasks

generate speech clone voices create audiobooks make podcasts dub videos

For Jobs:

speech therapist voice actor audio engineer podcaster youtuber

Alternative AI tools for metavoice-src

Similar Open Source Tools

metavoice-src

github

: 3.1k

llamabot

LlamaBot is a Pythonic bot interface to Large Language Models (LLMs), providing an easy way to experiment with LLMs in Jupyter notebooks and build Python apps utilizing LLMs. It supports all models available in LiteLLM. Users can access LLMs either through local models with Ollama or by using API providers like OpenAI and Mistral. LlamaBot offers different bot interfaces like SimpleBot, ChatBot, QueryBot, and ImageBot for various tasks such as rephrasing text, maintaining chat history, querying documents, and generating images. The tool also includes CLI demos showcasing its capabilities and supports contributions for new features and bug reports from the community.

github

: 176

mosec

Mosec is a high-performance and flexible model serving framework for building ML model-enabled backend and microservices. It bridges the gap between any machine learning models you just trained and the efficient online service API. * **Highly performant** : web layer and task coordination built with Rust 🦀, which offers blazing speed in addition to efficient CPU utilization powered by async I/O * **Ease of use** : user interface purely in Python 🐍, by which users can serve their models in an ML framework-agnostic manner using the same code as they do for offline testing * **Dynamic batching** : aggregate requests from different users for batched inference and distribute results back * **Pipelined stages** : spawn multiple processes for pipelined stages to handle CPU/GPU/IO mixed workloads * **Cloud friendly** : designed to run in the cloud, with the model warmup, graceful shutdown, and Prometheus monitoring metrics, easily managed by Kubernetes or any container orchestration systems * **Do one thing well** : focus on the online serving part, users can pay attention to the model optimization and business logic

github

: 834

Easy-Translate

Easy-Translate is a script designed for translating large text files with a single command. It supports various models like M2M100, NLLB200, SeamlessM4T, LLaMA, and Bloom. The tool is beginner-friendly and offers seamless and customizable features for advanced users. It allows acceleration on CPU, multi-CPU, GPU, multi-GPU, and TPU, with support for different precisions and decoding strategies. Easy-Translate also provides an evaluation script for translations. Built on HuggingFace's Transformers and Accelerate library, it supports prompt usage and loading huge models efficiently.

github

: 177

RAVE

RAVE is a variational autoencoder for fast and high-quality neural audio synthesis. It can be used to generate new audio samples from a given dataset, or to modify the style of existing audio samples. RAVE is easy to use and can be trained on a variety of audio datasets. It is also computationally efficient, making it suitable for real-time applications.

github

: 1.2k

ollama-ebook-summary

The 'ollama-ebook-summary' repository is a Python project that creates bulleted notes summaries of books and long texts, particularly in epub and pdf formats with ToC metadata. It automates the extraction of chapters, splits them into ~2000 token chunks, and allows for asking arbitrary questions to parts of the text for improved granularity of response. The tool aims to provide summaries for each page of a book rather than a one-page summary of the entire document, enhancing content curation and knowledge sharing capabilities.

github

: 459

deepeval

DeepEval is a simple-to-use, open-source LLM evaluation framework specialized for unit testing LLM outputs. It incorporates various metrics such as G-Eval, hallucination, answer relevancy, RAGAS, etc., and runs locally on your machine for evaluation. It provides a wide range of ready-to-use evaluation metrics, allows for creating custom metrics, integrates with any CI/CD environment, and enables benchmarking LLMs on popular benchmarks. DeepEval is designed for evaluating RAG and fine-tuning applications, helping users optimize hyperparameters, prevent prompt drifting, and transition from OpenAI to hosting their own Llama2 with confidence.

github

: 13.7k

TileRT

TileRT is a project designed to serve large language models (LLMs) in ultra-low-latency scenarios. It aims to push the latency limits of LLMs without compromising model size or quality, enabling models with hundreds of billions of parameters to achieve millisecond-level time per output token. TileRT prioritizes responsiveness for applications like high-frequency trading, interactive AI, real-time decision-making, long-running agents, and AI-assisted coding. It introduces a tile-level runtime engine that dynamically reschedules computation, I/O, and communication across multiple devices to minimize idle time and improve hardware utilization. The project is actively evolving, with compiler techniques gradually shared with the community through TileLang and TileScale.

github

: 588

kafka-ml

Kafka-ML is a framework designed to manage the pipeline of Tensorflow/Keras and PyTorch machine learning models on Kubernetes. It enables the design, training, and inference of ML models with datasets fed through Apache Kafka, connecting them directly to data streams like those from IoT devices. The Web UI allows easy definition of ML models without external libraries, catering to both experts and non-experts in ML/AI.

github

: 163

langchain

LangChain is a framework for developing Elixir applications powered by language models. It enables applications to connect language models to other data sources and interact with the environment. The library provides components for working with language models and off-the-shelf chains for specific tasks. It aims to assist in building applications that combine large language models with other sources of computation or knowledge. LangChain is written in Elixir and is not aimed for parity with the JavaScript and Python versions due to differences in programming paradigms and design choices. The library is designed to make it easy to integrate language models into applications and expose features, data, and functionality to the models.

github

: 1.1k

sdkit

sdkit (stable diffusion kit) is an easy-to-use library for utilizing Stable Diffusion in AI Art projects. It includes features like ControlNets, LoRAs, Textual Inversion Embeddings, GFPGAN, CodeFormer for face restoration, RealESRGAN for upscaling, k-samplers, support for custom VAEs, NSFW filter, model-downloader, parallel GPU support, and more. It offers a model database, auto-scanning for malicious models, and various optimizations. The API consists of modules for loading models, generating images, filters, model merging, and utilities, all managed through the sdkit.Context object.

github

: 164

talking-avatar-with-ai

The 'talking-avatar-with-ai' project is a digital human system that utilizes OpenAI's GPT-3 for generating responses, Whisper for audio transcription, Eleven Labs for voice generation, and Rhubarb Lip Sync for lip synchronization. The system allows users to interact with a digital avatar that responds with text, facial expressions, and animations, creating a realistic conversational experience. The project includes setup for environment variables, chat prompt templates, chat model configuration, and structured output parsing to enhance the interaction with the digital human.

github

: 132

storm

STORM is a LLM system that writes Wikipedia-like articles from scratch based on Internet search. While the system cannot produce publication-ready articles that often require a significant number of edits, experienced Wikipedia editors have found it helpful in their pre-writing stage. **Try out our [live research preview](https://storm.genie.stanford.edu/) to see how STORM can help your knowledge exploration journey and please provide feedback to help us improve the system 🙏!**

github

: 17.0k

YuE

YuE (乐) is an open-source foundation model designed for music generation, specifically transforming lyrics into full songs. It can generate complete songs in various genres and vocal styles, ensuring a polished and cohesive result. The model requires significant GPU memory for generating long sequences and recommends specific configurations for optimal performance. Users can customize the number of sessions for memory usage. The tool provides a quickstart guide for generating music using Transformers and includes tips for execution time and tag selection. The project is licensed under Creative Commons Attribution Non Commercial 4.0.

github

: 1.1k

agentscript

AgentScript is an open-source framework for building AI agents that think in code. It prompts a language model to generate JavaScript code, which is then executed in a dedicated runtime with resumability, state persistence, and interactivity. The framework allows for abstract task execution without needing to know all the data beforehand, making it flexible and efficient. AgentScript supports tools, deterministic functions, and LLM-enabled functions, enabling dynamic data processing and decision-making. It also provides state management and human-in-the-loop capabilities, allowing for pausing, serialization, and resumption of execution.

github

: 167

torchtitan

Torchtitan is a PyTorch native platform designed for rapid experimentation and large-scale training of generative AI models. It provides a flexible foundation for developers to build upon with extension points for creating custom extensions. The tool showcases PyTorch's latest distributed training features and supports pretraining Llama 3.1 LLMs of various sizes. It offers key features like multi-dimensional parallelisms, FSDP2 with per-parameter sharding, Tensor Parallel, Pipeline Parallel, and more. Users can contribute to the tool through the experiments folder and core contributions guidelines. Installation can be done from source, nightly builds, or stable releases. The tool also supports training Llama 3.1 models and provides guidance on starting a training run and multi-node training. Citation information is available for referencing the tool in academic work, and the source code is under a BSD 3 license.

github

: 5.1k

For similar tasks

metavoice-src

github

: 3.1k

wunjo.wladradchenko.ru

Wunjo AI is a comprehensive tool that empowers users to explore the realm of speech synthesis, deepfake animations, video-to-video transformations, and more. Its user-friendly interface and privacy-first approach make it accessible to both beginners and professionals alike. With Wunjo AI, you can effortlessly convert text into human-like speech, clone voices from audio files, create multi-dialogues with distinct voice profiles, and perform real-time speech recognition. Additionally, you can animate faces using just one photo combined with audio, swap faces in videos, GIFs, and photos, and even remove unwanted objects or enhance the quality of your deepfakes using the AI Retouch Tool. Wunjo AI is an all-in-one solution for your voice and visual AI needs, offering endless possibilities for creativity and expression.

github

: 820

Pandrator

Pandrator is a GUI tool for generating audiobooks and dubbing using voice cloning and AI. It transforms text, PDF, EPUB, and SRT files into spoken audio in multiple languages. It leverages XTTS, Silero, and VoiceCraft models for text-to-speech conversion and voice cloning, with additional features like LLM-based text preprocessing and NISQA for audio quality evaluation. The tool aims to be user-friendly with a one-click installer and a graphical interface.

github

: 429

ruoyi-ai

ruoyi-ai is a platform built on top of ruoyi-plus to implement AI chat and drawing functionalities on the backend. The project is completely open source and free. The backend management interface uses elementUI, while the server side is built using Java 17 and SpringBoot 3.X. It supports various AI models such as ChatGPT4, Dall-E-3, ChatGPT-4-All, voice cloning based on GPT-SoVITS, GPTS, and MidJourney. Additionally, it supports WeChat mini programs, personal QR code real-time payments, monitoring and AI auto-reply in live streaming rooms like Douyu and Bilibili, and personal WeChat integration with ChatGPT. The platform also includes features like private knowledge base management and provides various demo interfaces for different platforms such as mobile, web, and PC.

github

: 2.1k

viitor-voice

ViiTor-Voice is an LLM based TTS Engine that offers a lightweight design with 0.5B parameters for efficient deployment on various platforms. It provides real-time streaming output with low latency experience, a rich voice library with over 300 voice options, flexible speech rate adjustment, and zero-shot voice cloning capabilities. The tool supports both Chinese and English languages and is suitable for applications requiring quick response and natural speech fluency.

github

: 60

ebook2audiobook

ebook2audiobook is a CPU/GPU converter tool that converts eBooks to audiobooks with chapters and metadata using tools like Calibre, ffmpeg, XTTSv2, and Fairseq. It supports voice cloning and a wide range of languages. The tool is designed to run on 4GB RAM and provides a new v2.0 Web GUI interface for user-friendly interaction. Users can convert eBooks to text format, split eBooks into chapters, and utilize high-quality text-to-speech functionalities. Supported languages include Arabic, Chinese, English, French, German, Hindi, and many more. The tool can be used for legal, non-DRM eBooks only and should be used responsibly in compliance with applicable laws.

github

: 9.2k

HeyGem.ai

Heygem is an open-source, affordable alternative to Heygen, offering a fully offline video synthesis tool for Windows systems. It enables precise appearance and voice cloning, allowing users to digitalize their image and drive virtual avatars through text and voice for video production. With core features like efficient video synthesis and multi-language support, Heygem ensures a user-friendly experience with fully offline operation and support for multiple models. The tool leverages advanced AI algorithms for voice cloning, automatic speech recognition, and computer vision technology to enhance the virtual avatar's performance and synchronization.

github

: 2.5k

KlicStudio

Klic Studio is a versatile audio and video localization and enhancement solution developed by Krillin AI. This minimalist yet powerful tool integrates video translation, dubbing, and voice cloning, supporting both landscape and portrait formats. With an end-to-end workflow, users can transform raw materials into beautifully ready-to-use cross-platform content with just a few clicks. The tool offers features like video acquisition, accurate speech recognition, intelligent segmentation, terminology replacement, professional translation, voice cloning, video composition, and cross-platform support. It also supports various speech recognition services, large language models, and TTS text-to-speech services. Users can easily deploy the tool using Docker and configure it for different tasks like subtitle translation, large model translation, and optional voice services.

github

: 8.4k

For similar jobs

metavoice-src

github

: 3.1k

suno-api

Suno AI API is an open-source project that allows developers to integrate the music generation capabilities of Suno.ai into their own applications. The API provides a simple and convenient way to generate music, lyrics, and other audio content using Suno.ai's powerful AI models. With Suno AI API, developers can easily add music generation functionality to their apps, websites, and other projects.

github

: 1.7k

bark.cpp

Bark.cpp is a C/C++ implementation of the Bark model, a real-time, multilingual text-to-speech generation model. It supports AVX, AVX2, and AVX512 for x86 architectures, and is compatible with both CPU and GPU backends. Bark.cpp also supports mixed F16/F32 precision and 4-bit, 5-bit, and 8-bit integer quantization. It can be used to generate realistic-sounding audio from text prompts.

github

: 696

NSMusicS

NSMusicS is a local music software that is expected to support multiple platforms with AI capabilities and multimodal features. The goal of NSMusicS is to integrate various functions (such as artificial intelligence, streaming, music library management, cross platform, etc.), which can be understood as similar to Navidrome but with more features than Navidrome. It wants to become a plugin integrated application that can almost have all music functions.

github

: 713

ai-voice-cloning

This repository provides a tool for AI voice cloning, allowing users to generate synthetic speech that closely resembles a target speaker's voice. The tool is designed to be user-friendly and accessible, with a graphical user interface that guides users through the process of training a voice model and generating synthetic speech. The tool also includes a variety of features that allow users to customize the generated speech, such as the pitch, volume, and speaking rate. Overall, this tool is a valuable resource for anyone interested in creating realistic and engaging synthetic speech.

github

: 268

RVC_CLI

**RVC_CLI: Retrieval-based Voice Conversion Command Line Interface** This command-line interface (CLI) provides a comprehensive set of tools for voice conversion, enabling you to modify the pitch, timbre, and other characteristics of audio recordings. It leverages advanced machine learning models to achieve realistic and high-quality voice conversions. **Key Features:** * **Inference:** Convert the pitch and timbre of audio in real-time or process audio files in batch mode. * **TTS Inference:** Synthesize speech from text using a variety of voices and apply voice conversion techniques. * **Training:** Train custom voice conversion models to meet specific requirements. * **Model Management:** Extract, blend, and analyze models to fine-tune and optimize performance. * **Audio Analysis:** Inspect audio files to gain insights into their characteristics. * **API:** Integrate the CLI's functionality into your own applications or workflows. **Applications:** The RVC_CLI finds applications in various domains, including: * **Music Production:** Create unique vocal effects, harmonies, and backing vocals. * **Voiceovers:** Generate voiceovers with different accents, emotions, and styles. * **Audio Editing:** Enhance or modify audio recordings for podcasts, audiobooks, and other content. * **Research and Development:** Explore and advance the field of voice conversion technology. **For Jobs:** * Audio Engineer * Music Producer * Voiceover Artist * Audio Editor * Machine Learning Engineer **AI Keywords:** * Voice Conversion * Pitch Shifting * Timbre Modification * Machine Learning * Audio Processing **For Tasks:** * Convert Pitch * Change Timbre * Synthesize Speech * Train Model * Analyze Audio

github

: 71

openvino-plugins-ai-audacity

OpenVINO™ AI Plugins for Audacity* are a set of AI-enabled effects, generators, and analyzers for Audacity®. These AI features run 100% locally on your PC -- no internet connection necessary! OpenVINO™ is used to run AI models on supported accelerators found on the user's system such as CPU, GPU, and NPU. * **Music Separation**: Separate a mono or stereo track into individual stems -- Drums, Bass, Vocals, & Other Instruments. * **Noise Suppression**: Removes background noise from an audio sample. * **Music Generation & Continuation**: Uses MusicGen LLM to generate snippets of music, or to generate a continuation of an existing snippet of music. * **Whisper Transcription**: Uses whisper.cpp to generate a label track containing the transcription or translation for a given selection of spoken audio or vocals.

github

: 885

WavCraft

WavCraft is an LLM-driven agent for audio content creation and editing. It applies LLM to connect various audio expert models and DSP function together. With WavCraft, users can edit the content of given audio clip(s) conditioned on text input, create an audio clip given text input, get more inspiration from WavCraft by prompting a script setting and let the model do the scriptwriting and create the sound, and check if your audio file is synthesized by WavCraft.

github

: 347