2,000+ AI tools you can run locally Add tool

Moonshine

An on-device voice AI toolkit that combines speech recognition, intent recognition and text to speech across desktop, mobile and browser applications.

Screenshot of Moonshine website

Moonshine is an on-device AI toolkit for developers building voice agents and spoken interfaces. Voice processing runs on the device without an account or API keys.

Speech and intent recognition: Convert speech to text and recognize intent for applications that respond to spoken input.
Text to speech: Generate spoken responses within the same library used for transcription and conversational agents.
Live streaming: Process audio while someone is still speaking to reduce the wait before an application can respond.
Model choice: Choose speech recognition models suited to higher accuracy or constrained devices, with support for domain customization.

Moonshine supports macOS, Windows, Linux, iOS, Android and Raspberry Pi. Python and JavaScript/WASM support covers application development, including browser use, and a C API supports native integrations.

Speech-to-Text Models On-Device and In-Browser AI Speech-to-Text and Transcription Text-to-Speech and Audiobooks Voice Agent Frameworks macOS Windows Linux iOS Android Web Multilingual Streaming inference

Similar to Moonshine

Seamless Communication

1 video

Local AI translation models handle speech and text, with streaming translation and speech output that preserves voice style.

11.9KUpdated 2 months ago

macOS · Linux · Web#Batch processing#Hugging Face integration#Multilingual

Seamless Communication is Meta's family of AI models for developers and researchers building multilingual speech applications. It covers translation and transcription, with dedicated models for conversations and expressive speech.

Speech-to-Text and TranscriptionSpeech-to-Text ModelsText-to-Speech and AudiobooksText-to-Speech ModelsTranslation

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.

15.9KUpdated 1 day 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

Sokuji

2 videos

A live speech translator runs offline on your device, with translated voice and subtitles for desktop calls and supported Chrome and Edge meeting sites.

1.5KUpdated 4 days agoAGPL-3.0

macOS · Windows · Linux · Browser Extension#Multilingual#ONNX#OpenAI-compatible API

Sokuji translates speech for people taking part in meetings across languages. Other participants hear your translated voice as ordinary call audio, so they don't need to install anything.

On-Device and In-Browser AISpeech-to-Text and TranscriptionSubtitles and DubbingText-to-Speech and AudiobooksTranslation

Argmax OSS Swift

A Swift speech AI SDK runs Whisper, Pyannote and Qwen3-TTS on Apple Silicon for local transcription, speaker identification and speech generation.

6.5KUpdated 1 month agoMIT

macOS · iOS#Hugging Face integration#Multilingual#OpenAI-compatible API

Argmax OSS Swift is a speech AI SDK for developers building iOS and macOS apps that process audio on the user's device. Its separate libraries cover transcription, identifying speakers and generating spoken audio.

Inference Libraries and BindingsOn-Device and In-Browser AISpeech-to-Text and TranscriptionText-to-Speech and Audiobooks

Vocaldi

An offline dictation and text-to-speech app for Apple Silicon Macs. Speech processing stays on-device, with no app account required.

vocaldi.comDictation and Voice Typing

macOS#Multilingual#Works offline

Vocaldi is a paid Mac app that combines voice typing with read-aloud for people who prefer speaking to typing or listening to written text. Transcription, dictation cleanup and speech synthesis run on your Mac, so the audio and text you process stay on the device. It requires Apple Silicon and macOS 14 or later.

Dictation and Voice TypingOn-Device and In-Browser AISpeech-to-Text and TranscriptionText-to-Speech and Audiobooks

VibeVoice

3 videos

An open-source voice AI model family for local transcription and speech generation, with CPU recognition and streaming text-to-speech under the MIT license.

57.2KUpdated 1 month agoMIT

#Hugging Face integration#Multilingual#Quantization

VibeVoice is a family of voice AI models for developers and researchers building transcription and speech generation applications. It can capture who spoke and when, or produce spoken responses from incoming text.

Speech-to-Text and TranscriptionSpeech-to-Text ModelsText-to-Speech and AudiobooksText-to-Speech Models