voice AI (TTS, cloning, dictation)
Local-first open-source AI voice studio for voice cloning, TTS generation, system-wide dictation, and MCP-agent voice integration.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
Full local-first voice studio with cloning, TTS, dictation, and dubbing; a direct replacement for Voicebox's feature set.
VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
Narrower: Gradio web UI focused on Qwen3-TTS voice cloning, lacks system-wide dictation and multi-engine breadth.
A Gradio-based web UI for voice cloning and voice design, powered by Qwen3-TTS & VibeVoice. Can use Whisper or VibeVoice-ASR for automatic transcription.
Dictation-only alternative, no TTS or voice cloning.
Voice-to-text dictation app with local (Nvidia Parakeet/Whisper) and cloud models (BYOK). Privacy-first and available cross-platform.
Audiobook-focused multi-voice TTS studio, lacks cloning and system-wide dictation.
TTS-Story is a web-based multi‑voice TTS studio for turning tagged scripts into audiobooks—featuring full speaker management, chunk review/regeneration, a job queue and library system, and local GPU or API backends including Kokoro, Chatterbox, VOX CPM, Pocket-TTS, Kitten-TTS, IndexTTS-2, QWEN3 TTS and Omnivoice engines
Dictation-only app, local-first but lacks TTS and voice cloning.
🎙️ AI Dictation App - Open Source and Local-first ⚡ Type 3x faster, no keyboard needed. 🆓 Powered by open source models, works offline, fast and accurate.
Voice layer for AI agents (STT/TTS/VAD), narrower than Voicebox's full studio.
Opensource, on-device voice + vision layer for AI agents. Bring any model or coding agent; the whole speech loop (VAD, STT, TTS, barge-in) runs locally. An open alternative to ElevenLabs Agents, Gemini Live, and OpenAI Realtime.
Whisper-based dictation keyboard, single-feature tool.
A powerful Whisper AI keyboard for reliable speech transcription
Dictation and meeting recorder, no TTS or cloning.
Local voice dictation and meeting recorder for Windows + Linux. Hold a hotkey to dictate, or record long-form meetings with system audio. Whisper transcription, bring-your-own-LLM summaries. Open source.
Voice layer for AI agents, not a complete voice studio.
Sayna is a unified Voice Layer for AI Agents with a seemless integration to an existing agentic frameworks
Wispr Flow-style dictation app, without TTS or cloning.
Your personal voice interface for any app. Speak naturally and your words appear wherever your cursor is, with fully customizable AI voice dictation. Open source alternative to Wispr Flow.
These projects were analysed and named voicebox among their alternatives. The relationship is not symmetric — how voicebox rates them is a separate judgement, made when voicebox is analysed in its own right.
calls voicebox “Choose it when you prefer its engine set/UI or MLX-optimized stack over VoiceStudio; both are fully local voice studios.”
VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.
calls voicebox “an end-user voice studio app for cloning/dictating, not a library/model to integrate”
Open-Source Frontier Voice AI
calls voicebox “End-user AI voice studio, not a code-swappable TTS model.”
SoTA open-source TTS
calls voicebox “It's an end-user AI voice studio application, not a library you can embed.”
Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice cloning.