Open-source, fully local voice AI studio for macOS, Windows and Linux — voice cloning, voice design, dubbing, dictation and transcription in 646 languages.
Text-to-Speech
Turns written text into natural spoken audio, with control over voice, pace and delivery.
26 apps, 3 skills and 3 MCP servers tagged Text-to-Speech.
Apps
Free, fully on-device voice loop for AI coding agents — talk to Claude Code, Cursor or Codex and hear them answer back out loud.
Open-source inference engine that runs LLMs, vision and speech models fully on-device — no API keys, no cloud calls, from Swift to Godot.
Podcastle's successor: a remote multitrack recording studio plus a chat-driven AI editor that cleans audio, cuts clips, adds subtitles and hosts your podcast.
A text RPG platform run by an AI Game Master: play D&D 5e-style campaigns solo or with up to five friends in worlds you build or borrow.
An AI companion app where you design a character's personality, backstory, voice and look, then chat, call or roleplay with it across long-term memory.
Mac menu-bar OCR: drag over any part of the screen and the text in it lands on your clipboard, from videos, PDFs, images or apps.
ElevenLabs' reader app: turns PDFs, ePubs, articles and its own audiobook catalogue into speech using 1,000+ voices across 30+ languages.
Low-latency speech APIs from the team behind the open-source Dia model — text-to-speech and transcription priced well below the incumbents.
Wondershare's cross-platform video editor with AI auto-cut, object removal, dynamic captions and text-to-video built in.
A router for voice models: 56 speech and language models benchmarked across 10 languages, with each session sent to the one that actually wins.
Personal intelligence agent that tracks the topics you name across news, filings, forums and podcasts, folds duplicate coverage into one card, and briefs you by feed, push, email, RSS or audio.
Describe a video and get a complete edit — script, scenes, voiceover, and music — that you can refine by chatting.
Turn blog posts, scripts, and long recordings into narrated, captioned videos without editing software.
Listen to anything — documents, articles, PDFs, and email — in natural voices, at up to several times normal speed.
Enterprise speech infrastructure — fast, accurate transcription, text to speech, and a full voice agent API.
Voice AI that reads and expresses emotion — speech models trained on human vocal expression, not just phonemes.
Ultra-low-latency speech models built for real-time voice agents, where every millisecond is audible.
Studio-grade text to speech and voice cloning, with an open community library of thousands of voices.
Read-it-later app for articles, PDFs, EPUBs, newsletters, RSS and YouTube, with highlighting, AI chat and sync to Readwise reviews.
AI audio studio that turns prompts or documents into voiced podcasts and ads, with voice cloning, a timeline editor and team review.
AI avatar platform for scripted presenter videos and real-time conversational visual agents, with voice cloning and an API.
ByteDance's free video and photo editor for desktop, web and mobile, with auto-captions, templates and credit-based AI video generation.
Creates videos using AI avatars from text scripts
Build audio experiences at scale with Murf's AI voice generator
Generate lifelike spoken audio with AI tools
Skills
Skill: Showtime
by Favio Vazquez
Local video studio for coding agents: describe a video and your machine renders it, with voice-over, music and captions, no API keys.
Skill: MiniMax Multimodal Toolkit
by MiniMax AI
MiniMax's official skill for generating text, images, video, speech and music from the terminal through the mmx CLI, with agent-safe non-interactive flags.
NVIDIA's official skill for deploying and operating Nemotron Speech (Riva) NIMs — ASR, text-to-speech and translation, cloud-hosted or self-hosted on your own GPUs.
MCP servers
MiniMax's official MCP server for its media APIs: text to speech, voice cloning and voice design, image generation and editing, and Hailuo video generation.
MCP: VoiceStudio
by Palash Deb
Local speech MCP server bundled with VoiceStudio — generate speech, clone a voice from reference audio, and transcribe in 646 languages, all on your own machine with no API key.
MCP: Deepgram
by Deepgram
Deepgram's official MCP server, bringing speech-to-text, text-to-speech and audio intelligence into Claude Code, Cursor and Windsurf.
Related tags
Tags that appear alongside this one, ranked by how often.