Search Results for "gpt-sovits" - Page 5
Sort By:
Showing 196 open source projects for "gpt-sovits"
View related business solutions-
Gen AI apps are built with MongoDB AtlasMongoDB Atlas is the developer-friendly database used to build, scale, and run gen AI and LLM-powered apps—without needing a separate vector database. Atlas offers built-in vector search, global availability across 115+ regions, and flexible document modeling. Start building AI apps faster, all in one place.
-
GWI: On-demand Consumer ResearchNeed easy access to consumer insights? Our intuitive platform is the answer. Get the ultra-reliable research that brands and agencies need to stay ahead of changing consumer behavior.
-
1
Zypher Agent
A minimal yet powerful framework for creating AI agents
Zypher Agent is an open-source framework for building full-featured AI agents that can be embedded directly into applications, enabling reactive decision loops where the agent dynamically chooses its next actions. Unlike workflow-style orchestrators, it uses a reactive agent loop that interprets the task, reasons about next steps via LLMs, and integrates directly with extensible tools and external services. Zypher prioritizes native support for multiple model providers such as OpenAI and... -
2
WavTokenizer
SOTA discrete acoustic codec models with 40/75 tokens per second
WavTokenizer is a state-of-the-art discrete acoustic codec designed specifically for audio language modeling, capable of compressing 24 kHz audio into just 40 or 75 tokens per second while preserving high perceptual quality. It is built to represent speech, music, and general audio with extremely low bitrate, making it ideal as a front-end for large audio language models like GPT-4o and similar architectures. The model uses a single-quantizer design together with temporal compression to achieve extreme compression without sacrificing reconstruction fidelity. Its architecture incorporates a broader vector-quantization space, extended contextual windows, and improved attention networks, combined with multi-scale discriminators and inverse Fourier transform blocks to enhance waveform reconstruction. ... -
3
Griptape
Python framework for AI workflows and pipelines with chain of thought
The Griptape framework provides developers with the ability to create AI systems that operate across two dimensions: predictability and creativity. For predictability, Griptape enforces structures like sequential pipelines, DAG-based workflows, and long-term memory. To facilitate creativity, Griptape safely prompts LLMs with tools (keeping output data off prompt by using short-term memory), which connects them to external APIs and data stores. The framework allows developers to transition... -
4
ChatGPT Academic
ChatGPT extension for scientific research work
...All buttons are dynamically generated by reading functional.py, you can add custom functions at will, and liberate the pasteboard. Support for markdown tables output by GPT. If the output contains a formula, it will be displayed in tex form and rendered form at the same time, which is convenient for copying and reading. -
Powerful Business Process AutomationWhen a message is received ThinkAutomation automatically executes one or more Automations. Automations are created using an easy to use drag-and-drop interface to run simple or complex tasks. Automations can perform many business process Actions, including: updating company databases, CRM systems and cloud services, sending outgoing emails, Teams & SMS messages, document processing, custom scripting, integration and much more. Over 100 built-in actions are included, plus ThinkAutomation is extensible with Custom Actions.
-
5
GPTel
A no-frills ChatGPT client for Emacs
...It will ask you for the key if you skipped the previous step. Run it with a prefix-arg to start a new session. In the gptel buffer, send your prompt with M-x gptel-send, bound to C-c RET. Set chat parameters (GPT model, directives etc) for the session by calling gptel-send with a prefix argument. -
6
spacy-transformers
Use pretrained transformers like BERT, XLNet and GPT-2 in spaCy
spaCy supports a number of transfer and multi-task learning workflows that can often help improve your pipeline’s efficiency or accuracy. Transfer learning refers to techniques such as word vector tables and language model pretraining. These techniques can be used to import knowledge from raw text into your pipeline, so that your models are able to generalize better from your annotated examples. You can convert word vectors from popular tools like FastText and Gensim, or you can load in any... -
7
Qwen3-Omni
Qwen3-omni is a natively end-to-end, omni-modal LLM
...It achieves state-of-the-art results: across 36 audio and audio-visual benchmarks, it hits open-source SOTA on 32 and overall SOTA on 22, outperforming or matching strong closed-source models such as Gemini-2.5 Pro and GPT-4o. To reduce latency, especially in audio/video streaming, Talker predicts discrete speech codecs via a multi-codebook scheme and replaces heavier diffusion approaches. -
8
Penzai
A JAX research toolkit to build, edit, & visualize neural networks
Penzai, developed by Google DeepMind, is a JAX-based library for representing, visualizing, and manipulating neural network models as functional pytree data structures. It is designed to make machine learning research more interpretable and interactive, particularly for tasks like model surgery, ablation studies, architecture debugging, and interpretability research. Unlike conventional neural network libraries, Penzai exposes the full internal structure of models, enabling fine-grained... -
9
Tarsier
Vision utilities for web interaction agents
At Reworkd, we iterated on all these problems across tens of thousands of real web tasks to build a powerful perception system for web agents... Tarsier! In the video below, we use Tarsier to provide webpage perception for a minimalistic GPT-4 LangChain web agent. Tarsier visually tags interactable elements on a page via brackets + an ID e.g. [23]. In doing this, we provide a mapping between elements and IDs for an LLM to take actions upon (e.g. CLICK [23]). We define interactable elements as buttons, links, or input fields that are visible on the page; Tarsier can also tag all textual elements if you pass tag_text_elements=True. ... -
The most advanced C and C++ source code analyzerTrustInSoft Analyzer is a C and C++ source code analyzer powered by formal methods, mathematical & logical reasonings that allow for exhaustive analysis of source code. This analysis can be run without false positives or false negatives, so that every real bug in the code is found. Developers receive several benefits: a user-friendly graphical interface that directs developers to the root cause of bugs, and instant utility to expand the coverage of their existing tests. Unlike traditional source code analysis tools, TrustInSoft’s solution is not only the most comprehensive approach on the market but is also progressive, instantly deployable by developers, even if they lack experience with formal methods, from exhaustive analysis up to a functional proof that the software developed meets specifications.
-
10
Haystack
Haystack is an open source NLP framework to interact with your data
...Perform semantic search and retrieve ranked documents according to meaning, not just keywords! Make use of and compare the latest pre-trained transformer-based languages models like OpenAI’s GPT-3, BERT, RoBERTa, DPR, and more. Pick any Transformer model from Hugging Face's Model Hub, experiment, find the one that works. Use Haystack NLP components on top of Elasticsearch, OpenSearch, or plain SQL. Boost search performance with Pinecone, Milvus, FAISS, or Weaviate vector databases, and dense passage retrieval. -
11
LLaVA
Visual Instruction Tuning: Large Language-and-Vision Assistant
Visual instruction tuning towards large language and vision models with GPT-4 level capabilities. -
12
ChatGPT Java
A Java client for the ChatGPT API
ChatGPT Java is a Java client for the ChatGPT API. Use official API with model gpt-3.5-turbo. -
13
GParted
A partition editor to graphically manage disk partitions
GNOME Partition Editor for creating, reorganizing, and deleting disk partitions. It uses libparted from the parted project to detect and manipulate partition tables. Optional file system tools permit managing file systems not included in libparted.">
-
14
qt-fsarchiver
Program for Backup and restore partitions
qt-fsarchiver is a GUI for the program fsarchiver to save/restore partitions, folders and MBR/GPT. Clone from hard disk and partitions is possible. The program is for systems based Debian, for Suse and Fedora. Look: (German language) http://wiki.ubuntuusers.de/qt-fsarchiver. Language: German, English, Spain, Russia, Chinese and Italian and more. Notes in Readme (Liesmich) for install in Suse, Fedora and Debian based systems.">
-
15
VividNode
Multi-purpose Text & Image Generation Desktop Chatbot
A cross-platform AI desktop chatbot application for LLM such as GPT, Claude, Gemini, Llama chatbot interaction and image generation, offering customizable features, local chat history, and enhanced performance—no browser required! -
16
-
17
AIEditorApp
Privacy-first desktop application for LLMs and AI APIs
🚀 Cross-platform desktop application. 💻 Works on Mac, Windows, and Linux. 🗂️ All chat data is stored locally. 🗄️ Local templates and logs. 🤖 Use any AI model of your choice. -
18
Windows Install
Installing Windows from macOS. Suitable for Hackintosh and Macintosh
The Windows Install.app program allows you to install Windows directly from the Mac OS system. There is no need to create an installation flash drive. Suitable for Hackintosh and Macintosh (install drivers yourself). Possibility to make a backup. There is a drag and drop support function. Compatible with Mac OS X 10.13 and up. The utilities used are wimlib and ntfs-3g and others. Disk access must be granted (shown in the screenshot) The user must be an administrator and the...">
-
19
PrizeRebel
The PrizeRebel Rewards App provides an easy way to access PrizeRebel.
A popular GPT (Get-Paid-To) platform where users can earn rewards by completing surveys, watching videos, and completing offers. This app simplifies the process by offering a streamlined browsing experience, allowing users to earn points faster and redeem them for PayPal cash, gift cards, and more. Start earning today with just a few taps!">
-
20
Mr. Ranedeer
GPT-4 AI Tutor Prompt for customizable personalized learning
Unlock the potential of GPT-4 with Mr. Ranedeer AI Tutor, a customizable prompt that delivers personalized learning experiences for users with diverse needs and interests. -
21
...It offers a plethora of features to ensure you make profitable trades effortlessly. With Solana Ultimate Ai Trade Bot, you can also create and manage tokens on the Solana network. The bot is powered by GPT-4o, providing real-time AI support for all your needs.
-
22
OpenAI-Java
OpenAI Api Client in Java
OpenAI-Java is the official Java client library provided by OpenAI for interacting with the OpenAI API. It is designed to make it easier for Java applications to call endpoints like chat completions, embeddings, function calling, streaming, and other model services using idiomatic Java patterns. You configure the client (often via environment variables or system properties), then build parameter objects (e.g. ChatCompletionCreateParams) and invoke methods like... -
23
VOIP-VOICE-TO-TEXT&ANALYS
Convert VoIP calls to text and analyze them with AI
The VoIP voice-to-text software for Issabel is an intelligent, AI-based solution that converts calls into accurate Persian text. After each call, the audio file is sent to the GPT-4O AI engine, producing editable transcripts. The software also provides AI-powered call analysis, extracting key points, customer requests, satisfaction levels, and sensitive topics, all stored in the database. This helps sales and support teams make faster decisions, improve response quality, and enhance customer experience. Fully compatible with Issabel and open-source VoIP systems, the software runs securely on internal networks without external services. ... -
24
Modern UI/UX GPT-3
Master the creation of Modern UX/UI Websites
This repository teaches how to craft a modern marketing site with polished UI/UX patterns using React and CSS. It focuses on layout, typography, spacing, and component structure to produce a landing page feel often seen in contemporary product sites. The project encourages clean semantics and reusable components while keeping the stack lightweight. It’s positioned as a design-driven build rather than a data-heavy app, making it ideal for practicing hero sections, feature blocks, responsive... -
25
AppFlowy
Bring projects, wikis, and teams together with AI.
AppFlowy is an AI collaborative workspace where you can achieve more without losing control of your data. It is the best open source alternative to Notion, offering a 100% offline mode and self-hosting with a cloud service of your choice. Build a centralized workspace for your wiki, projects, and notes with AppFlowy. It allows you to organize and visualize your data in tables, Kanban boards, calendars, and more. You can filter and sort your data in any way you want. AppFlowy comes...