Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.

A high-performance, cross-platform TTS synthesis solution powered by ONNX Runtime, featuring support for streaming output and low-latency playback, as well as custom voice profiles and mixed Chinese-English generation. 基于 ONNX Runtime 的跨平台高性能 TTS 合成方案，支持流式输出与低延迟播放，支持自定义音色与中英混合生成。

Get started using Deepgram's Live Text-to-Speech with this Node demo app

Get started using Deepgram's Live Text-to-Speech with this Flask demo app

Get started using Deepgram's Live Text-to-Speech with this Go demo app

Get started using Deepgram's Live TTS with this FastAPI demo app

Get started using Deepgram's Live Text-to-Speech with this Bun demo app

Real-time embodied multi-agent voice assistant for the NAO H25 humanoid. SAGE-CBT research platform with streaming TTS, lazy GPT-4o vision, hybrid face-first wake, 47 native gestures, sound-source localization, and a hardcoded 988 crisis gate.

Get started using Deepgram's Live TTS with this Deno demo app

Real chunk-level streaming for Qwen3-TTS on MLX (first audio in ~317ms)

Get started using Deepgram's Live TTS with this Django demo app

Offline AI sidecar for games: local tiny LLM (llama.cpp Vulkan, Qwen3-4B), streaming STT (sherpa-onnx Nemotron) and token-streaming TTS (Kyutai Pocket TTS) behind an OpenAI-compatible localhost API. Any engine, any GPU vendor, no cloud tokens.

Get started using Deepgram's Live Text-to-Speech with this C++ demo app

Get started using Deepgram's Live Text-to-Speech with this Java demo app

Get started using Deepgram's Live Text-to-Speech with this Rust demo app

Get started using Deepgram's Live Text-to-Speech with this PHP demo app

Privacy-first local voice assistant with streaming LLM-to-TTS pipeline

HAL 9000 voice cloning with Qwen3-TTS streaming - OpenAI-compatible REST API

OpenVINO-only Qwen3-TTS runtime/exporter with native low-latency streaming sidecar for Linux/Windows, VoiceDesign, CustomVoice, VoiceClone, and prebuilt release packages.

基于 VoxCPM2 的 HTTP TTS 服务，面向 Legado 与有声书场景，支持零样本音色克隆、多角色路由、流式语音合成、ASR 提示词自动生成及跨平台部署。