Search Results for "voice"
Sort By:
Showing 83 open source projects for "voice"
View related business solutions-
Train ML Models With SQL You Already KnowBuild and deploy ML models using familiar SQL. Automate data prep with built-in Gemini. Query 1 TB and store 10 GB free monthly.
-
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
1
Moonshine Voice
Fast and accurate automatic speech recognition (ASR) for edge devices
moonshine is an open-source automatic speech recognition toolkit optimized for fast and accurate transcription on edge devices and local environments. The project is designed to enable real-time voice applications such as live transcription, voice commands, and embedded speech interfaces without requiring heavy cloud infrastructure. Its architecture emphasizes low latency and flexible input handling, allowing audio streams of varying durations rather than relying on fixed processing windows. Moonshine supports multiple platforms including mobile, desktop, and embedded systems, and provides example projects to accelerate integration into real-world products. ... -
2
Concat
Open-Source CapCut replacement (MCP supported)
...Core editing tools include splitting, trimming, merging, transitions, and playback-speed adjustment. Offline features include automatic captions, local text-to-speech voices, voice processing, titles, and styled text. Templates allow reusable edit structures to be applied across projects. Concat is currently in beta and targets macOS, Windows, and Linux with a multilingual interface. -
3
PersonaPlex
PersonaPlex code
...This architectural approach eliminates awkward pauses and makes conversations feel much more human-like, with natural behaviors such as overlapping speech, interruptions, and fluent turn-taking, traits that traditional AI assistants typically lack. PersonaPlex also supports persona and voice control, allowing developers to define the role and speaking style of the agent using text prompts and voice conditioning, making it suitable for applications like customized voice assistants, interactive character agents, or domain-specific conversational tools. Internally, it processes continuous audio streams in a hybrid input format so that speech understanding and generation occur jointly. -
4
Kaset
The missing YouTube Music macOS app
Kaset is a social audio platform framework that allows users to host, share, and interact with audio content in community-oriented spaces, combining elements of podcasting, voice rooms, and feedback-driven discovery. It provides an interface where creators can upload episodes, host live or scheduled voice sessions, and cultivate listener communities through comments, reactions, and follow systems. The platform emphasizes audio discovery with playlists, curated channels, and trending audio feeds, helping users find relevant voice content without sifting through noise. ... -
Build Data Resilience - Take the Assessment TodayIs your recovery strategy as strong as you think? Take this quick self-assessment to check your recovery readiness and gain tailored insights. In only 2 minutes, you'll learn where you fall on the recovery readiness scale.
-
5
Qwen Audio Agent
A realtime voice runtime that keeps Agents talking
Qwen Audio Agent is a real-time voice runtime designed to keep an AI assistant conversationally present while it performs longer tasks. It supports full-duplex speech, natural interruption, and continuous multi-turn dialogue. Direct questions are answered immediately, while tool-intensive work can be delegated to a background coding agent without ending the voice session. -
6
Speakr
Speakr is a personal, self-hosted web application
Speakr is an open-source, real-time text-to-speech (TTS) web application that allows users to convert written text into natural-sounding speech in just a few clicks. It provides a clean, user-friendly interface where users can input text, choose a voice style or language, and immediately hear the output, making it ideal for accessibility, content creation, and learning applications. Behind the scenes, Speakr leverages modern TTS engines and streaming audio technologies to deliver smooth and responsive speech generation without noticeable delay. The project is built with extensibility in mind, enabling developers to add custom voices, integrate additional languages, and tailor the backend for different hardware or cloud environments. ... -
7
Translate-Subtitle-File
Subtitle Creation Assistant
Subtitle group machine translation assistant - [Function 1: Translate subtitle file] .srt .ass .vtt [Function 2: Voice to text] (Drag in video or audio to recognize subtitles) (The latest version v4.1.0 Update time 2021 2 May 23) 12 translation service providers can be configured, such as Google, Baidu, Tencent, Caiyun, IBM, Azure, Amazon, etc. (6 voice service providers can be configured: Alibaba Cloud, Xunfei, Tencent Cloud, IBM, Azure, Amazon ) Advantages: 1. -
8
FFsubsync
Automagically synchronize subtitles with video
...In this case, you can use the correctly synchronized srt file directly as a reference for synchronization, instead of using the video as the reference. ffsubsync uses the file extension to decide whether to perform voice activity detection on the audio or to directly extract speech from an srt file. ffsubsync usually finishes in 20 to 30 seconds, depending on the length of the video. -
9
Textream
Textream is a free macOS teleprompter app for streamers, interviewers
...It runs natively on macOS and leverages on-device speech recognition to highlight each word in real time as you speak, keeping your focus where it belongs — on delivery rather than memorization. The interface supports multiple modes of use, such as classic constant-scroll auto-scrolling, voice-activated scrolling that pauses when you’re silent, and direct word tracking that syncs the displayed script to your spoken pace. Textream also includes flexible display modes, from a sleek notch-anchored overlay on laptops to an invisible-to-the-audience floating window or fullscreen experience. -
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
10
OpenVINO AI Plugins for Audacity
A set of AI-enabled effects, generators, and analyzers for Audacity
A set of AI-enabled effects, generators, and analyzers for Audacity. These AI features run 100% locally on your PC, no internet connection is necessary. OpenVINO™ is used to run AI models on supported accelerators found on the user's system such as CPU, GPU, and NPU. -
11
SpotSeekBot
spotify music downloader telegram bot (tracks, albums, playlists)
SpotSeekBot is a Discord music bot designed to stream and control Spotify-based playback within voice channels. It allows users to search for tracks, play songs, and manage queues directly through chat commands. The bot integrates with Spotify APIs to retrieve track information and playlists while using external sources for actual audio playback. It supports common playback controls such as pause, skip, and seek, enabling interactive music sessions in real time. -
12
RHVoice
Free open source speech synthesizer for Russian and other languages
RHVoice is a free and open-source multilingual speech synthesizer. Its developers hope to give more visually impaired people the ability to use a good free synthesis voice reading in their native language with their screen reader. We are especially interested in supporting those languages for which there are currently no good voices that could be used with a screen reader. The creator of RHVoice, Olga Yakovleva, is blind herself. Many of the contributors to the RHVoice project, both programmers and non-programmers, are blind or partially sighted. -
13
Music-bot
A complete code to download for a cool Discord music bot
Music-bot is a Discord bot designed to stream and manage music playback within voice channels, providing users with an interactive audio experience. It supports playing music from various online sources, including streaming platforms and direct URLs. The bot includes queue management features that allow users to add, remove, and reorder tracks during playback. It integrates audio processing tools to ensure smooth streaming and consistent playback quality. -
14
MediaDevices
Go implementation of the MediaDevices API
...It provides a cross-platform, unified API for capturing and manipulating media streams and is often used in combination with Pion WebRTC for peer-to-peer communications. Its support for device enumeration, media constraints, and frame processing makes it a powerful building block for custom voice and video solutions in Go. -
15
Music Assistant
Music Assistant is a free, opensource Media library manager
...The server is designed to run on an always-on device such as a Raspberry Pi, NAS, Intel NUC, or similar home server. It can work as a standalone product, but it is especially tailored for Home Assistant users who want automation, voice control, and smart-home playback workflows. Music Assistant supports features such as library matching, metadata enrichment, gapless playback, crossfade, volume normalization, synchronized playback, announcements, and queue transfers. It is a strong choice for users who want one organized media layer across different music services and playback devices. -
16
AudioNotes
Extract audio and video content and organize it into a Markdown note
AudioNotes is an application (or proof-of-concept) that likely combines audio recording or playback with note-taking or annotation functionality — enabling users to record voice or audio and attach textual or timestamped notes, making it ideal for lectures, interviews, meetings, or personal memos. Such a tool offers a more expressive and flexible way to capture and revisit information: instead of just typed notes or raw audio, users get both audio context and structured notes. As an open-source repository, AudioNotes provides developers or power users the opportunity to customize how audio is captured, stored, annotated, and replayed — e.g. adding playback speed control, export to standard formats, or synchronization between notes and audio timeline. ... -
17
Voxal voice changer
Transform your voice in real-time voxal voice changer
Voxal Voice Changer is a program that allows you to modify your voice by applying various effects (e.g. pitch change, echo, etc.) in real-time. Effects can be added in any sequence and in any combination, allowing you to distort your voice beyond recognition. Take your audio to the next level! Our powerful Voice Changer software lets you morph your voice in real-time with stunning AI-powered quality. -
18
annyang!
Speech recognition for your site
annyang is a tiny javascript library that lets your visitors control your site with voice commands. annyang supports multiple languages, has no dependencies, weighs just 2kb and is free to use. annyang understands commands with named variables, splats, and optional words. Use named variables for one word arguments in your command. Use splats to capture multi-word text at the end of your command (greedy). Use optional words or phrases to define a part of the command as optional. annyang plays nicely with all browsers, progressively enhancing browsers that support SpeechRecognition, while leaving users with older browsers unaffected. ... -
19
byzorgan
Specialized sound synthesizer with Byzantine Church music scales
This software integrates a small, specialized synthesizer and vocal processor. It can be used to learn Byzantine Church singing. You can play from the keyboard, mouse or touch screen. MIDI input is also available. Voice functions include: pitch highlighting, synthesizer control by voice, pitch correction and voice-to-ison conversion. On the screen there are labels with symbols of Byzantine notes. There is a metronome. The program is oriented on the Chrysanthos tuning of the diatonic scale: 9/8 - 12/11 - 88/81. The octave is divided into 17 (or 19) non-equal parts, it allows you to get all the Byzantine modes. -
20
WO Mic
Transform your smartphone into a PC microphone
WO Mic is a free utility that turns your smartphone into a functional microphone for your Windows PC. It eliminates the need to buy a separate microphone, offering a convenient and cost-effective solution for voice chat, recording, or wireless voice control. The app supports multiple connection types including Wi-Fi, Bluetooth, and USB, giving users flexible options to suit their setup. Setup involves installing the mobile app and the PC client with drivers, which is straightforward and fast. While USB connections provide the best audio quality and lowest latency, Wi-Fi and Bluetooth offer greater wireless freedom. ... -
21
Audio Satanifier 666
Easily apply cool gnarly voice filters to your audio files
...Its more focused on the "satan voice" filter, while the larger default version has 16 different filters you can mix and match. (Source code is included within the html file itself.) -
22
Mechvibes
Play mechanical keyboard sounds, typewriter sound as you type
It's a side project that I made for myself since when I use my own mechanical keyboard at late night or in the office and my parents and my coworkers hate that a lot because the sound of the keyboard is very loud (especially in quiet places). So if you are facing this issue just like me then this product is for you! - Plays typewriter sound - You can add more keyboard sound set by recording any sound you like and add them to this app with some easy steps. - Use your laptop keyboard... -
23
Lenstube
Decentralized video-sharing social media platform
Decentralized video-sharing social media platform, built using Lens protocol. This turborepo uses Yarn as a package manager. For a place to have open discussions on features, voice your ideas, or get help with general questions please visit our community at Discord. -
24
NAMp
Load multiple .nam files and change between them live
NAMp plays Neural Amp Modeler captures the way an amp's gain knob actually works. Point it at a folder of captures of the same amp taken at ascending gain settings. The Capture knob sweeps through them continuously instead of loading one fixed voice. Adjacent captures are cross faded rather than hot-swapped, so there is no click at the crossings and no level jump between files; on the audio thread that costs two models while the knob is moving and one at rest. It works just as well as a plain 64-slot capture switcher if your captures aren't a gain sweep. Four banks for captures that you can switch betwwen live using midi. ... -
25
50mb
Audio Tools, Sound, Experiments, WAV, library
...Now includes sound libs; But can be used as royalty free sample packs for music creation commercial projects with no extra issues. Use them as you would with a music keyboard voice / tone, or as a sample library CD disk from back in the day (this is exactly what this is but without the actual CD disk hence digital download version). Raw PCM wav data. Saved as .bin (binary) format as fresh from development, but the PCM data is ready to use as a .wav file for usage convenience. If you have issues try importing them and converting them in a sound editor or renaming them, to the .wav file extension. ...
