1,700+ AI tools you can run locally Add tool

Silero VAD

A voice activity detection model finds speech segments in audio, with local PyTorch or ONNX processing and an MIT license.

Silero VAD is a pretrained voice activity detection model for developers who need to find speech segments in audio. It returns speech timestamps for use in audio processing pipelines.

The model runs locally with PyTorch, and ONNX Runtime supports CPU or GPU execution. Applications that already load audio can pass it directly to the detector; optional audio components provide file reading and writing. It's open source under the MIT license. The Python examples require at least 1 GB of RAM and a modern x86-64 CPU with AVX, AVX2, AVX-512 or AMX instructions.

Open Models On-Device and In-Browser AI Voice, Speech and Music Web Batch processing Multilingual ONNX Voice activity detection Works offline

Similar to Silero VAD

Moshi

A local voice AI model and dialogue framework that listens while speaking, with MLX support for Mac and iPhone and self-hosted server backends.

11.3KUpdated 5 months agoApache-2.0

macOS · iOS · Web#Hugging Face integration#MLX#Quantization

Moshi is a voice AI model and dialogue framework for researchers and developers building spoken applications. It processes speech directly and can listen while it speaks, including information such as emotion and non-verbal cues.

Inference Servers and ClustersOn-Device and In-Browser AIOpen ModelsVoice Agent FrameworksVoice Assistants

Whisper

34 videos

An MIT-licensed speech recognition model for local transcription, multilingual audio and translation into English, with several model sizes.

110.7KUpdated 2 months agoMIT

#Multilingual#Voice activity detection

Whisper is an open source speech recognition model for transcribing recordings on your own hardware. It's for developers building voice features and people working with multilingual audio.

Speech-to-Text and TranscriptionSpeech-to-Text Models

sherpa-onnx

1 video

An open-source speech toolkit that runs ONNX models locally for transcription, speech synthesis and speaker analysis on desktop, mobile and embedded devices.

15.3KUpdated 21 hours agoApache-2.0

macOS · Windows · Linux · iOS · Android · Web#Multilingual#ONNX#Speaker diarization

sherpa-onnx is a toolkit for developers building speech features that work offline on their own devices. It covers transcription, speech generation and audio analysis, with processing kept local.

Inference Libraries and BindingsOn-Device and In-Browser AISpeech-to-Text and TranscriptionStem Separation and Audio CleanupText-to-Speech and Audiobooks

Candle

2 videos

An open-source Rust machine learning framework runs models locally on CPUs, CUDA GPUs and in browsers, with support for quantized LLMs.

21.2KUpdated 3 days agoApache-2.0

macOS · Web#GGUF#Hugging Face integration#Multilingual

Candle is a Rust machine learning framework for developers embedding local AI in applications or deploying models on their own servers. It supports inference and training, including small CPU deployments for serverless applications.

Inference Libraries and BindingsOn-Device and In-Browser AITraining Frameworks

NativeMind

A local AI browser extension that uses Ollama to chat across tabs, analyze files and help with writing, with no account required.

1.1KUpdated 7 months agoAGPL-3.0

Web · Browser Extension#Multilingual#Multimodal input#Ollama integration

NativeMind is a local ChatGPT alternative for people who want AI help with reading and writing inside their browser. It processes prompts and page content on your device using local models.

Browser AI SidebarsChat With Your DocumentsOn-Device and In-Browser AITranslationWriting and Email Assistants

ReScript

1 video

A transcript-based video and audio editor that works offline in a browser or on macOS, Windows and Linux, with local Whisper transcription.

936Updated 2 weeks ago

macOS · Windows · Linux · Web#ONNX#Speaker diarization#Streaming inference

ReScript is a video and audio editor for people cutting interviews, podcasts and voice notes through text. Deleting words from a transcript removes the matching sections of the recording.

On-Device and In-Browser AISpeech-to-Text and TranscriptionSubtitles and Dubbing