Speech

A lightweight native C++ inference runtime for NVIDIA's Nemotron speech model family, covering streaming speech recognition, speaker diarization, speech translation and text-to-speech, powered by ggml with broad hardware support.

• Inference
• Speech

A local-first AI voice studio that clones voices, synthesizes speech through seven TTS engines, provides system-wide dictation, and connects MCP agents to custom voices.

• Speech

An open-source omnimodal large language model that combines image, speech and text understanding with real-time, emotionally expressive speech generation.

• Models
• Speech

A Python tool that fine-tunes Qwen3-TTS on a few minutes of audio to clone a voice and generate speech locally on your own GPU, from a CLI or web UI.

• Speech

An on-device speech SDK for Android offering streaming speech recognition, text-to-speech, voice activity detection, and noise cancellation, built on ONNX Runtime with Qualcomm NNAPI acceleration.

• Speech

A high-performance serving implementation of Qwen3-TTS that streams speech over HTTP and WebSocket with under 50 milliseconds to first audio at 10 requests per second on a single H100.

• Speech

A curated list of papers, code, and resources for speech language models and end-to-end speech dialogue systems, covering understanding, benchmarks, and full-duplex modeling.

• Speech
• Papers

A from-scratch reimplementation of the Qwen3-ASR speech recognition model for Apple's MLX framework, running natively on Apple Silicon GPUs without PyTorch.

• Speech

An open-source realtime media server in Go that handles the WebRTC transport, barge-in, and streaming speech-to-text, LLM, and text-to-speech pipeline behind a voice agent, so a developer keeps their own prompts, tools, and models while StreamCore owns the latency-sensitive path.

• Speech
• Backend

A lightweight, on-device voice-activity-detection engine that flags when someone is speaking in an audio stream, with SDKs and demo applications for Python, .NET, C, Android, iOS, web and Node.js.

• Speech

An open-source desktop agent that combines a voice character with real coding-agent-style work, letting a user speak or type naturally while specialized providers execute delegated tasks and the character narrates progress and asks for permission.

• Coding agents
• Speech

A local-first speech-to-text engine, built in Rust on the ggml inference library, that transcribes audio entirely on-device through an OpenAI-compatible API, with no cloud calls and no telemetry.

• Speech

An open-source, on-device voice and vision layer that gives any AI model or coding agent real-time speech input and output, screen or camera awareness, and the ability to be interrupted mid-reply.

• Speech

Open-source, self-hosted infrastructure for real-time voice AI telephony agents in Indian languages, with swappable speech-to-text, text-to-speech, LLM and telephony providers.

• Speech

A local-first voice AI runtime providing transcription, speaker diarization, text-to-speech, and voice cloning through a desktop app, web UI, CLI, and an OpenAI-compatible local API.

• Speech

Open-source voice typing for Windows: press a shortcut, speak, and AI-cleaned-up text is inserted at the cursor, using local models, the user's own API keys, or a self-hosted backend.

• Speech

A cross-platform toolkit for running language models, speech recognition and text-to-speech natively inside apps and games, on Flutter, Swift, Kotlin, Unity or Rust, entirely offline.

• Inference
• Speech

An on-device speech-to-text engine SDK from Picovoice that runs entirely locally across desktop, mobile and web platforms, with bindings for Python, C, iOS, Android, Node.js, Flutter, React Native, Java, .NET and the browser.

• Speech

A family of Arabic-first, generative speech-recognition models that treat transcription as audio-conditioned next-token prediction rather than CTC decoding, covering Modern Standard Arabic, major dialects, code-switched Arabic-English and English.

• Speech

A local text-to-speech tool that runs Qwen3-TTS models on Apple Silicon Macs through MLX, with voice cloning, voice design and built-in voices, fully offline.

• Speech

A low-latency, streaming automatic speech recognition model that commits transcribed text permanently as it arrives, without revising earlier words, for uses such as live captioning and voice-driven agents.

• Speech

Cheetah is an on-device streaming speech-to-text engine from Picovoice that transcribes audio locally in real time, without sending voice data to the cloud.

• Speech

A single C++ binary offering 119 speech backends, including 62 text-to-speech engines, for automatic speech recognition, text-to-speech, forced alignment, and translation, with no Python dependency at runtime.

• Speech

Rhino is an on-device speech-to-intent engine from Picovoice that infers a spoken command's intent and slot values directly, in real time, for a defined set of voice commands.

• Speech