voicestudio

VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.

🗣 Java Text to Speech (JSAPI2) engines (google cloud, cocoa, open jtalk, aquestalk(ゆっくり), voicevox(ずんだもん), coeiroink, aivisspeech, google genai, qwen3-tts, voicestudio)

voice studio plugin for hermes agent

Run VoiceStudio free on a Google Colab T4 GPU — voice cloning, video dubbing, TTS and transcription with zero local GPU. Remote-GPU setup for the open-source ElevenLabs alternative.

Text-to-speech (TTS) for Twitch, YouTube and Kick. Custom voices, viewer assignments and Streamer.bot automation in a Windows app.

Telegram bot wrapper for VoiceStudio TTS & voice cloning

MCP server wrapper for VoiceStudio (debpalash): local voice cloning & TTS via OmniVoice on DGX Spark. ASMR DSP pipeline included.

VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.

Creative workflows for VoiceStudio and six ArtCraft apps: social graphics, voiceovers, animation, and video editing.

VoiceStudio packaged for LazyCat Cloud

Dictation Turbo — a system add-on for Mac: double-tap Control anywhere, speak, and the text lands at your cursor. 646 languages via the free, open-source VoiceStudio — nothing to buy.

A voice AI companion for Windows and Linux. Create characters with ComfyUI, give them voices, emotions and memories. Local models, cloud APIs or your Hermes agent; speech powered by VoiceStudio.