speaker free download - SourceForge

Showing 232 open source projects for "speaker"

View related business solutions
  • Host LLMs in Production With On-Demand GPUs Icon
    Host LLMs in Production With On-Demand GPUs

    NVIDIA L4 GPUs. 5-second cold starts. Scale to zero when idle.

    Deploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
    Start Free
  • Our Free Plans just got better! | Auth0 Icon
    Our Free Plans just got better! | Auth0

    With up to 25k MAUs and unlimited Okta connections, our Free Plan lets you focus on what you do best—building great apps.

    You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
    Try free now
  • 1
    sherpa-onnx

    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.
    Downloads: 203 This Week
    Last Update:
    See Project
  • 2
    Open-XiaoAI

    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. ...
    Downloads: 3 This Week
    Last Update:
    See Project
  • 3
    VibeVoice ComfyUI

    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. ...
    Downloads: 2 This Week
    Last Update:
    See Project
  • 4
    Buzz

    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.
    Downloads: 522 This Week
    Last Update:
    See Project
  • Build Agents and Models on One Platform Icon
    Build Agents and Models on One Platform

    Everything you need to build production-ready agents and models. Access 200+ Google and third-party AI models and tools.

    Gemini 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.
    Start Free
  • 5
    xiaogpt

    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. ...
    Downloads: 1 This Week
    Last Update:
    See Project
  • 6
    VoiceStudio

    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.
    Downloads: 365 This Week
    Last Update:
    See Project
  • 7
    OuteTTS

    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.
    Downloads: 2 This Week
    Last Update:
    See Project
  • 8
    FireRedTTS-2

    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.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 9
    MiGPT-Next

    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. ...
    Downloads: 1 This Week
    Last Update:
    See Project
  • Endpoint Management with Remote Control Built In Icon
    Endpoint Management with Remote Control Built In

    Patch, monitor, and connect to Windows and macOS devices from one console

    Save 50% on your first year when you switch from your existing RMM to Splashtop AEM. Automate patching, track inventory, and jump directly into 1-click unattended remote sessions without switching tools.
    Start Free Trial
  • 10
    WhisperX

    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.
    Downloads: 35 This Week
    Last Update:
    See Project
  • 11
    Choragus

    Choragus

    native macOS Sonos controller and now much more for Apple Silicon

    ...Listening history, statistics, and Last.fm scrobbling provide insight into music habits. Optional AI tools generate playlists and allow assistants to control speakers through MCP. Local network communication keeps speaker control independent of cloud accounts.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 12
    reveal.js

    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. ...
    Downloads: 5 This Week
    Last Update:
    See Project
  • 13
    OpenWhispr

    OpenWhispr

    Voice-to-text dictation app with local (Nvidia Parakeet/Whisper)

    ...The application supports multilingual dictation, translation, and integration with AI assistants for voice-driven tasks. It also offers meeting transcription with speaker identification and searchable notes. Its local processing options keep recorded audio on the user's device without requiring cloud transmission. Available for Windows, macOS, and Linux, OpenWhispr combines voice input, intelligent automation, and configurable transcription workflows.
    Downloads: 25 This Week
    Last Update:
    See Project
  • 14
    Beamer

    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. ...
    Downloads: 24 This Week
    Last Update:
    See Project
  • 15
    Scriberr

    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.
    Downloads: 31 This Week
    Last Update:
    See Project
  • 16
    Biscotti

    Biscotti

    Free private meeting transcription app for macOS

    ...It captures microphone and system audio from virtual meetings or in-person conversations without requiring a bot to join calls. The application processes recordings locally using on-device speech recognition and AI models. It generates speaker-labeled transcripts, meeting summaries, action items, and suggested titles. Calendar integration helps identify upcoming meetings, while automatic call detection can stop recordings when conversations end. Users can add timestamp-linked Markdown notes and configure custom vocabulary for specialized terminology. Biscotti also provides MCP integration for interacting with meeting records through compatible AI applications, keeping recordings and transcripts stored locally rather than in the cloud.
    Downloads: 1 This Week
    Last Update:
    See Project
  • 17
    VibeVoice

    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. ...
    Downloads: 7 This Week
    Last Update:
    See Project
  • 18
    Clips Studio

    Clips Studio

    Free open-source AI video clipper

    ...It analyzes Twitch, Kick, YouTube, podcasts, and other footage to identify engaging moments using speech, audio, and visual activity. Its multimodal scoring system evaluates potential clips based on excitement, reactions, and narrative impact. Automatic speaker tracking reframes footage into vertical videos suitable for Shorts, Reels, and TikTok. The application generates synchronized captions and provides editing tools for refining clips before export. Users can process content locally with Whisper and Ollama or connect supported cloud AI models. Additional capabilities include multilingual captions, AI dubbing, sports highlight detection, and automated publishing. ...
    Downloads: 4 This Week
    Last Update:
    See Project
  • 19
    Real-Time Voice Cloning

    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. ...
    Downloads: 3 This Week
    Last Update:
    See Project
  • 20
    VoxCPM

    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.
    Downloads: 4 This Week
    Last Update:
    See Project
  • 21
    Whisper-WebUI

    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.
    Downloads: 10 This Week
    Last Update:
    See Project
  • 22
    MegaTTS 3

    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.
    Downloads: 1 This Week
    Last Update:
    See Project
  • 23
    OpenVoiceOS

    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.
    Downloads: 2 This Week
    Last Update:
    See Project
  • 24
    ioquake3

    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.
    Downloads: 17 This Week
    Last Update:
    See Project
  • 25
    TranscriptionSuite

    TranscriptionSuite

    A fully local and private Speech-To-Text app

    ...Users can choose among AI transcription engines, including Whisper, NVIDIA NeMo, SenseVoice, and VibeVoice. The software provides real-time dictation, long-form transcription, and automatic speaker identification. Its Audio Notebook organizes recordings through a searchable calendar interface with optional AI assistance. Users can export transcripts as text or subtitle files and use global shortcuts for dictation. TranscriptionSuite also supports GPU acceleration, remote connections, and compatible API integrations. Available for Windows, macOS, and Linux, it processes audio locally without mandatory cloud services.
    Downloads: 14 This Week
    Last Update:
    See Project
  • Previous
  • You're on page 1
  • 2
  • 3
  • 4
  • 5
  • Next