Search Results for "speaker"
Sort By:
Showing 150 open source projects for "speaker"
View related business solutions-
Demo Series - Small Business Backup By VeeamWatch this on-demand demo series and learn how to protect your Microsoft 365 data with clear, simple, actionable steps that are easy to implement for businesses of all sizes.
-
Paessler: Easy to Use With Enterprise Power. Free TrialYou shouldn't have to choose between a monitoring tool that's easy to use and one that's powerful enough for a complex environment. PRTG's low-code interface lets any admin build dashboards, set alerts and monitor devices without scripting, while custom sensors and full API access are there when your team needs deeper control. One platform, no compromise. Download a free 30-day trial now.
-
1
sherpa-onnx
Speech-to-text, text-to-speech, and speaker recognition
Speech-to-text, text-to-speech, and speaker recognition using next-gen Kaldi with onnxruntime without an Internet connection. Support embedded systems, Android, iOS, Raspberry Pi, RISC-V, x86_64 servers, websocket server/client, C/C++, Python, Kotlin, C#, Go, NodeJS, Java, Swift, Dart, JavaScript, Flutter. -
2
Open-XiaoAI
Let the Xiaoai speaker "hear your voice"
Open-XiaoAI is an open-source framework that takes deeper control of compatible Xiaomi XiaoAI smart speakers by accessing their audio input and output paths. It extends the earlier MiGPT concept beyond cloud API responses and enables developers to build custom voice experiences directly around the speaker hardware. Demonstrations include custom wake words, Xiaozhi AI integration, MiGPT integration, Gemini Live API access, and stereo pairing. The architecture uses separate client and server components, with the client running on modified speaker firmware. Official instructions target the XiaoAI Speaker Pro LX06 and Xiaomi Smart Speaker Pro OH2P. ... -
3
VibeVoice ComfyUI
ComfyUI integration for Microsoft's VibeVoice text-to-speech model
VibeVoice ComfyUI is a comprehensive wrapper that integrates Microsoft’s VibeVoice text-to-speech models directly into ComfyUI workflows. It exposes VibeVoice as a set of custom nodes so you can build single-speaker and multi-speaker voice generation pipelines visually, combining TTS with other audio or generative components. The integration supports high-quality single-speaker synthesis as well as scripted multi-speaker conversations, with optional voice cloning from audio samples for each speaker. It includes advanced control over generation parameters like attention backend, diffusion steps, sampling temperature, guidance scale, and quantization settings, allowing users to tune the trade-offs between quality, VRAM usage, and speed. ... -
4
Buzz
Buzz transcribes and translates audio offline
...Live microphone transcription supports real-time captions and a presentation view for accessible events. Speech separation can improve results on noisy recordings, while speaker identification distinguishes voices within transcribed media. Multiple Whisper backends, Transformer models, and GPU acceleration options provide flexibility across different computers. Transcripts can be searched, reviewed alongside playback, exported in common subtitle formats, automated through a CLI, or extended with plugins. -
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.
-
5
xiaogpt
Play ChatGPT and other LLM with Xiaomi AI Speaker
xiaogpt is a Python project that connects Xiaomi AI speakers with ChatGPT and other large language models. It lets users turn compatible XiaoAI speaker devices into conversational AI assistants beyond the default built-in voice capabilities. The project works by listening for user interactions, forwarding prompts to supported model providers, and sending generated responses back through the speaker. It supports multiple operating modes, wake-word styles, and model backends depending on the user’s setup. ... -
6
VoiceStudio
VoiceStudio is the open-source, fully-local ElevenLabs alternative
...It can clone voices from short reference recordings or design new voices from characteristics such as accent, pitch, age, and delivery style. Video dubbing combines transcription, translation, speaker preservation, speech synthesis, and final video export. It also supports multi-voice stories, audiobooks, dictation, vocal isolation, and speaker diarization. Multiple TTS and speech-recognition engines can run through CUDA, Apple Silicon, ROCm, or CPU hardware. Desktop, API, MCP, remote-worker, and batch-processing interfaces make it suitable for both interactive and automated workflows while keeping core processing local by default. -
7
FireRedTTS-2
Long-form streaming TTS system for multi-speaker dialogue generation
...FireRedTTS2 supports multilingual output and speaker flexibility, enabling scenarios that involve language switching, cross-lingual voice cloning, and expressive dialogue generation that maintains consistency over longer utterances. -
8
WhisperX
Automatic Speech Recognition with Word-level Timestamps
...The system enables batched inference, significantly increasing transcription speed while maintaining high accuracy. It is particularly effective for long recordings, where traditional approaches may suffer from drift, repetition, or misalignment. whisperx also supports speaker diarization, allowing identification of different speakers within a conversation. Its architecture combines multiple components to enhance both performance and usability in real-world transcription tasks. Overall, whisperx provides a more robust and scalable solution for high-quality speech-to-text applications. -
9
OuteTTS
Interface for OuteTTS models
...It also includes a notion of speaker profiles: you can create a speaker from a short audio sample, save it as JSON, and reuse it for consistent voice identity across generations and sessions. For best quality, the model is designed to work with a reference speaker clip and will inherit emotion, style, and accent from that reference. -
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
10
OpenVoiceOS
OpenVoiceOS Core, the FOSS Artificial Intelligence platform
...It can also use persona support to route fallback conversations to LLM-backed solvers when normal skills do not answer a request. ovos-core is useful for builders who want a community-driven, extensible voice assistant stack instead of a closed smart-speaker platform. -
11
reveal.js
The HTML Presentation Framework
reveal.js is a framework for creating beautiful interactive presentations using HTML. It comes with a wide range of features, including nested slides, auto-sliding, touch navigation, Markdown support, PDF export, speaker notes, theming and more. It also comes with a JavaScript API that allows you to control various other options, and a list of plugins that can be used to extend reveal.js further. reveal.js currently offers full support for any recently released version of the following browsers: Chrome, Safari, Firefox, Opera, Edge and IE10-11. ... -
12
reveal-md
reveal.js on steroids. Get beautiful reveal.js presentations
...Running it against a Markdown document starts a local server and renders the content as interactive slides. Authors can separate slides with configurable syntax and include highlighted code blocks, speaker notes, and YAML front matter. Themes, syntax-highlighting styles, custom CSS, scripts, templates, favicons, and reveal.js options provide extensive presentation customization. Live reload automatically updates the presentation while the Markdown source is being edited. Presentations can also be exported to PDF or built as static websites, although the project is no longer under active feature development. -
13
VibeVoice
Open-source multi-speaker long-form text-to-speech model
VibeVoice-1.5B is Microsoft’s frontier open-source text-to-speech (TTS) model designed for generating expressive, long-form, multi-speaker conversational audio such as podcasts. Unlike traditional TTS systems, it excels in scalability, speaker consistency, and natural turn-taking for up to 90 minutes of continuous speech with as many as four distinct speakers. A key innovation is its use of continuous acoustic and semantic speech tokenizers operating at an ultra-low frame rate of 7.5 Hz, enabling high audio fidelity with efficient processing of long sequences. ... -
14
MiGPT-Next
Let the Xiaoai speaker "listen to you"
MiGPT-Next is an upgraded branch of the MiGPT concept focused on customizable responses for Xiaomi XiaoAI smart speakers. It lets developers intercept recognized messages and define how the speaker should respond through programmable handlers. The project can connect to OpenAI-compatible model endpoints and allows configuration of models, API URLs, headers, system prompts, and speaker credentials. It can be launched through Docker or installed as the @mi-gpt/next Node.js package. Unlike the earlier MiGPT release, the newer implementation removed continuous conversation and streaming response support because of API latency and device-state limitations. ... -
15
Beamer
A LaTeX class for producing presentations and slides
The beamer class is focused on producing (on-screen) presentations, along with support material such as handouts and speaker notes. Content is created in a frame environment, each of which can be divided up into a number of slides (actual output pages). A simple 'action' notation is used to specify which material appears on each slide within a frame. The class supports a range of environments to enable complex slide relationships to be constructed. The appearance of slides is controlled by a template system. ... -
16
MegaTTS 3
Official PyTorch Implementation
...Its backbone is a lightweight diffusion-transformer (on the order of ~0.45 B parameters), which enables efficient inference while still producing high-fidelity audio. Given a reference audio sample (and corresponding latent representation), MegaTTS3 can generate speech in the style and voice timbre of that speaker — useful for personalized TTS, voice-overs, dubbing, or multi-speaker applications. The system supports both Chinese and English (with code-switching), making it versatile across languages, and offers controls for accent strength, voice similarity, intelligibility vs. similarity tradeoffs, and other speech parameters to fine-tune output. -
17
Real-Time Voice Cloning
Clone a voice in 5 seconds to generate arbitrary speech in real-time
Real-Time Voice Cloning is an influential deep-learning repository that demonstrates how to clone a voice from just a few seconds of audio and then generate arbitrary speech in that voice in near real time. It implements the SV2TTS pipeline (“Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis”) in three stages: a speaker encoder, a synthesizer, and a vocoder. In the first stage, short audio clips are converted into a fixed-dimensional speaker embedding that captures voice characteristics; this embedding is then used by a Tacotron-style synthesizer to generate spectrograms from text, which a WaveRNN-based vocoder finally turns into audio. ... -
18
Whisper-WebUI
A Web UI for easy subtitle using whisper model
...It supports multiple input sources including local files, YouTube content, and microphone input, making it versatile for different workflows. Whisper WebUI also includes advanced preprocessing and postprocessing features such as voice activity detection, background music separation, and speaker diarization, enabling more accurate and structured outputs. -
19
VoxCPM
TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning
...Trained on a large 1.8-million-hour bilingual corpus, VoxCPM can infer appropriate speaking style from context, dynamically adjusting intonation, rhythm, and emotional tone. It supports zero-shot voice cloning from a short reference audio clip, capturing timbre, accent, and pacing to closely mimic a target speaker without per-speaker fine-tuning. -
20
Open Notebook
An Open Source implementation of Notebook LM with more flexibility
...Open Notebook enables users to organize and analyze multi-modal content such as PDFs, videos, audio files, web pages, and Office documents. It combines full-text and vector search with context-aware AI chat to deliver insights grounded in your own research materials. With advanced features like multi-speaker podcast generation, customizable content transformations, and a comprehensive REST API, Open Notebook provides a powerful and extensible research environment. -
21
ioquake3
The ioquake3 community effort to continue supporting/developing id's
...The engine modernizes the original codebase with a CMake build system, an SDL2 backend for cross-platform windowing and input, and OpenAL sound for better audio quality and multi-speaker setups. It adds numerous quality-of-life improvements such as VoIP support, AVI demo capture, improved console completion and history, and optional Ogg Vorbis support. ioquake3 also improves portability and maintainability by supporting x86_64 on Linux, MinGW builds on Windows, and various other operating systems, and even provides web support via Emscripten. -
22
DramaBox
super expressive prompting model based on ltx2.3
...It also supports additional LoRA training on top of DramaBox, making it possible to adapt the model for a specific speaker, language flavor, or performance style. DramaBox is aimed at developers, researchers, and audio creators who need highly expressive English TTS for character dialogue, narrative audio, prototyping, or voice experimentation. -
23
The SpeechBrain Toolkit
A PyTorch-based Speech Toolkit
...SpeechBrain supports state-of-the-art methods for end-to-end speech recognition, including models based on CTC, CTC+attention, transducers, transformers, and neural language models relying on recurrent neural networks and transformers. Speaker recognition is already deployed in a wide variety of realistic applications. SpeechBrain provides different models for speaker recognition, including X-vector, ECAPA-TDNN, PLDA, and contrastive learning. Spectral masking, spectral mapping, and time-domain enhancement are different methods already available within SpeechBrain. Separation methods such as Conv-TasNet, DualPath RNN, and SepFormer are implemented as well. ... -
24
sonoscli
Control SONOS speakers from your terminal
sonoscli is a modern command-line interface for controlling Sonos speaker systems directly from the terminal using local network communication protocols. Written in Go, the tool allows users to discover, group, and manage Sonos devices without relying on the official desktop or mobile applications. It supports playback controls, room grouping, queue management, favorites, live event subscriptions, and Spotify integration while maintaining a scriptable interface suitable for automation workflows. ... -
25
Scriberr
Self-hosted AI audio transcription
...Unlike cloud-based transcription services, Scriberr runs entirely on the user’s machine, ensuring that sensitive recordings are never sent to third-party servers and remain fully under user control. It leverages modern speech recognition models such as Whisper and other advanced architectures to deliver precise transcripts with word-level timing and speaker identification. The application includes a polished user interface that simplifies the management of recordings, transcripts, and annotations, making it suitable for both casual users and professionals handling large volumes of audio. Beyond transcription, Scriberr also integrates features such as summarization, tagging, and interaction with language models, allowing users to extract insights from conversations or meetings efficiently.
