NobodyWho
NobodyWho is an open-source, on-device inference library and SDK that runs text, vision, and speech models (LLM, STT, TTS) locally across platforms, emphasizing performance, privacy, and offline use.
NobodyWho is ai tools software teams evaluate for voice & speech. Use this page to review pricing, integration signals, and the best alternatives before you commit.
Profile facts come from the vendor source. AiMatch labels unknown pricing or API details instead of estimating them.
Review official source →Quick Overview
Best for: Voice & Speech
What it does
AI Tools software for decision-makers comparing workflow fit and alternatives.
Best fit
Voice & Speech
Pricing snapshot
Free from $0
Next step
Compare NobodyWho with similar tools before you shortlist it.
Compare this tool before you shortlist it
Review alternatives, pricing posture, and workflow fit side by side.
NobodyWho
NobodyWho is an open-source on-device inference library and SDK designed to run text, vision, and speech models locally without servers. It provides SDKs and examples (Chat, STT, TTS) across multiple languages and platforms so developers can integrate AI with minimal code. The project emphasizes fast, optimized inference (Metal, CUDA, Vulkan), strict local privacy (no cloud logging, offline operation), and broad model compatibility (GGUF format and Hugging Face model URIs). The library is licensed under EUPL 1.2 and is free for individuals and companies.
Run AI models on any device Discussion | Link
Own this listing?
Claim this page for a one-time $29 to add pricing, features, screenshots, verified owner details, and a clearly labeled 30-day category position after the profile is live.
Claim this listing for $29Key Features
On-device LLM, STT, and TTS
Provides SDKs and runtime support for chat (LLM), speech-to-text (STT), and text-to-speech (TTS) with code examples in multiple languages.
Multi-platform SDKs
Platform bindings and examples for React Native, Flutter, Kotlin, Swift, Python, and Godot, plus explicit platform support for Apple, Android, Windows, and Linux.
High-performance inference
Optimized kernels for Metal, CUDA, and Vulkan to deliver fast inference even on integrated graphics and mobile chips.
Privacy & offline-first
Designed to keep data local: no cloud logging, prompts remain in local GPU memory, and models can run offline in secure environments.
Model compatibility
Direct support for GGUF format and the ability to pick models from Hugging Face; examples reference HF URIs (e.g., hf://onnx-community/whisper-base).
Open-source and permissive for companies
The library is open source under EUPL 1.2 and stated to be free for both individuals and companies.
Pricing
Completely free, no API keys, or usage fees.
Free
$0- Open-source library under EUPL 1.2
- No API keys or usage fees
Use Cases
On-device chat assistants
Embed chat/LLM functionality directly in apps using Chat.fromPath with local GGUF models for low-latency, private responses.
Speech transcription
Use STT.transcribeFile with locally hosted models (e.g., onnx-community/whisper) to transcribe audio without sending data to the cloud.
Text-to-speech for apps
Synthesize speech locally with Tts.load and save WAV output for offline or private TTS in applications.
Secure and offline deployments
Run models on-device for scenarios requiring no internet connectivity or strict data locality, such as in-flight or secure environments.
Integrations
Hugging Face
Pick and run models hosted on Hugging Face; site advises selecting models from Hugging Face and supports HF URIs.
onnx-community (Whisper)
STT examples reference hf://onnx-community/whisper-base for speech transcription.
Third-party model authors (Mistral, Qwen, Gemma, Liquid, OpenAI listed)
The site lists model names (Mistral, Open AI, Liquid, Qwen, Deepseek, Gemma) as supported model sources or examples.
Benefits
Limitations
No verified limitations are available.
Frequently Asked Questions
No verified FAQs are available.
Getting Started
- 1 Explore the Docs and pick a model from Hugging Face or a GGUF model.
- 2 Install or import the NobodyWho SDK for your platform (examples shown for React Native, Flutter, Kotlin, Swift, Python, Godot).
- 3 Load a model path (e.g., Chat.fromPath({ modelPath: "./model.gguf" })) and call the provided APIs (ask, transcribeFile, synthesize) to run inference locally.
Support
docs
Documentation referenced on the site (Docs link in navigation).
github
Project and source code available via GitHub (link in site navigation).
community
Community channels listed on the site (Discord and social links).
Email contact is listed in the site footer/navigation (explicit address not shown).
API
Compare NobodyWho with similar tools
See how it stacks up against alternatives
Related Tools
View all 76 →
Join the Mic Captions beta
Mic Captions (beta) is a TestFlight beta app that turns spoken audio into real-time, easy-to-read captions on iPhone and iPad, with translation, session saving, transcript replay, and navigation by Topics and Words.
respeecher
Respeecher is a professional AI voice technology company offering real-time Text-to-Speech (TTS) and voice cloning services—providing production-grade synthetic voices, a marketplace of AI voices, a Pro Tools plugin, and white-glove services for film, TV, games, podcasts, and enterprise customers.
Nicevoice
NiceVoice is a free web-based AI voice cloning tool that creates high-quality synthetic voices from 5–30 seconds of audio using neural networks. It offers a three-step workflow (upload sample, AI clone, generate & download), supports English and Chinese, and emphasizes speed, accuracy, and data encryption.
Affiliatepartner-freshcaller
Freshcaller (Freshdesk Contact Center) is a cloud-based contact center and voice platform from Freshworks offering intelligent IVR, call routing, voice AI, omnichannel conversation handling, and analytics for businesses of all sizes.
Vibevoice
VibeVoice AI is an open-source Microsoft Research framework for long-form, multi-speaker text-to-speech that can generate up to 45–90 minutes of continuous, context-aware audio with support for up to four distinct speakers and English/Chinese outputs, distributed under an MIT license with pretrained weights on GitHub and Hugging Face.
Dupdub
DupDub is an all-in-one AI-powered content creation platform for creators and businesses that offers AI writing, text-to-speech and voice cloning, AI avatars (talking photos), video editing, transcription, translation and localization across 90+ languages to streamline content production and distribution.
Premium Alternatives
bswan-ai
Bswan is a managed conversion infrastructure platform that uses AI voice and messaging funnels to activate new users, recover early churn, and increase lifetime value by running telephony, messaging, routing, tracking and continuous optimization for campaigns at scale.
sigma-ai
SigmaMind AI (sigma-ai) is a voice AI platform that creates deployable voice agents for call centers to handle outbound and inbound campaigns—lead generation, debt collection, appointment setting, and customer support—integrating with existing dialers and CCaaS stacks.
talkforce-ai
TalkForce AI provides AI-powered voice/call agents that automate customer service conversations—handling routine inquiries, bookings, cancellations, and outbound calls—while integrating with existing systems and handing off to humans when needed.