LMNT text-to-speech provider adapter for genblaze
Speakvora SDK: text to speech, speech to text, phrase library, offline packs, voice agents and live streaming.
Shunyalabs ASR & TTS services for Pipecat
MCP server that gives Claude, Cursor and other AI agents a voice: generate voiceovers, multi-speaker dialogue and SRT/VTT subtitles with the Miragea API.
Tujia text-to-speech: Ye pinyin to 16 kHz waveform (single-speaker, ONNX)
Kokoro TTS integration for Vision Agents
Open-source Cantonese (Hong Kong) text-to-speech — CPU-first ONNX inference SDK
Offline-first Kokoro text-to-speech CLI and localhost service
my dash mic recorder
Open-source multi-speaker video dubbing: transcribe, find who speaks when, translate, and re-voice every speaker with their own cloned voice, with timing fit, ducked background, dubbed MP4, multi-language audio track and SRT/VTT. CLI + MCP server + Agent Skill, voiced by Miragea.
Full-Stream Zero-shot TTS model with Extremely Low Latency and Speaking-rate Control
HolosTTS text-to-speech on PyTorch
Chatterbox MLX: Open Source TTS and Voice Conversion for MLX. Based off of Chatterbox by Resemble AI
Text-to-speech CLI, MCP server, and Claude Code plugin (ElevenLabs, AWS Polly, OpenAI)
Open-source AI voiceover and faceless video generator: turn a script into text-to-speech narration, SRT subtitles and YouTube / Shorts / TikTok videos with word-by-word captions. Free voices, no API key.
Open-source AI podcast generator: turn any URL, PDF, text or topic into a two-host (or panel) podcast with distinct voices, chapters, SRT/VTT transcript and RSS. CLI + MCP server + Agent Skill, voiced by Miragea.
An Open Source text-to-speech system built by inverting Whisper
Fish Audio TTS and STT integration for Vision Agents
StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models. Original authors: Yinghao Aaron Li, Cong Han, Vinay S. Raghavan, Gavin Mischler, Nima Mesgarani.
Phonemiser, text normaliser, transliterator and pronunciation engine for text-to-speech and speech recognition: 44 languages, Apache-2.0.
Orca Streaming Text-to-Speech Engine
Open-source AI audiobook maker: turn an EPUB, Markdown or text file into a chaptered M4B audiobook (chapter markers, cue sheet, per-chapter MP3) in a cloned narrator voice. CLI, no GPU. Voiced by Miragea.
A Python library for normalizing Vietnamese text for TTS and NLP applications
LinnetTTS: lightweight on-device text-to-speech (native runtime)
Kalpa text-to-speech services for Pipecat
Antalia-2 Mini: small Turkish text to speech, one synthetic voice, 7.6M parameters, 48 kHz, faster than real time on a CPU
Форк библиотеки speakerpy с потоковой TTS, генерацией чанков аудио и улучшениями
Official Vocea SDK for Python: text-to-speech, voice cloning and transcription
Local speech, narration with frame-accurate timings for video, and music made from code: Kokoro, Edge and macOS voices, cloned voices (Chatterbox, GPU on Apple silicon), speech to text (Parakeet), voice FX, bytebeat.
Finesse text-to-speech for Pipecat
Local neural TTS server with hooks for Claude Code, OpenCode, and GitHub Copilot CLI
Free, offline pronunciation trainer for English and Spanish. Speech synthesis, recognition and scoring run on your computer.
MCP server bridging Claude with Google Gemini (video, music, voice, images, Deep Research, agents, 1M context) and 400+ OpenRouter models
统一的文本转语音(TTS)工具库,支持多种开源TTS引擎和字幕格式
AI-powered audiobook generator with GPU/NPU acceleration (up to 10x faster than real-time). Built-in Kokoro-82M TTS with character-aware voices and dialogue detection. Interactive chapter stripping to remove unwanted content. Supports EPUB, PDF, TXT, MD, RST (use convertext for DOCX/MOBI/HTML).
Hebrew Text-to-Speech inference using ONNX and TensorRT
Local, private, hands-free voice for any AI agent: speech in and out on your own machine, nothing leaves it.
A Python package for converting PDF and TXT files to audio
Standalone local WebSocket text-to-speech (TTS) server, client, and pluggable mlx-audio backends for the Pipecat ecosystem
Real-time text-to-speech on Intel NPU/CPU via OpenVINO
Pre-alpha, open, local speech-to-text and text-to-speech: licence-checked manifest, hash-verified downloads, transcribe() and synthesize() with a Whisper engine (optional extra) and an Indic Parler-TTS engine (own environment). Every model is unverified.
star — Speaking Terminal Access Reader: accessible study tools for reading and writing, with built-in text-to-speech
Python package for convert text to phoneme ipa, use for cross language embedding Text-to-speech Reseach
Offline Japanese text-to-speech with Kokoro-82M (int8 ONNX), no downloads at runtime