[ Premium ] Fusion Voice v1.0.1.0

  • Thread starter Thread starter B0u3Zizi
  • Start date Start date
  • Reading time: 2 minutes

Latest Update 3 Nov 2026

B0u3Zizi

value="{NN}"
Administrator
20 Mar 2019
1,105
7,485
Tunisia
FusionVoice - Desktop AI Voice Studio for TTS, Voice Cloning & Audiobooks

WebSite: FusionVoice. Stop Renting Your Voice. Own It. | Desktop AI Voice Studio​

Price: $67 / Free for Premium Members

FusionVoice.png


FusionVoice is a desktop app for Windows and Mac that lets you generate, clone, design, and direct AI voices, right on your own computer. Four AI voice engines run free and local, so there is no per-character meter, no monthly fee, and no internet required for the core work. You pay once and it is yours.

But it is a lot more than a text-to-speech box. I packed it with the tools I actually use:

Quick TTS: paste a script, pick a voice, generate in about a second
Voice Clone: clone your voice from a few seconds of audio, stored on your disk
Voice Lab: design a brand-new voice just by describing it
Studio: type one sentence and get a full multi-voice production
Audiobooks: turn a manuscript into narrated audio, chapter by chapter
7 engines in one app: 4 free local, plus OpenAI, Gemini & ElevenLabs
Translate 200+ languages without leaving the app
Speak in 600+ languages using local AI engines inside the app

Download

/

Hidden content
You need to reply to this thread in order to see this content.
Or upgrade your account. See details
 
Fusion Scribe v1.0.0.6

✔ improved many features in the qwen3 tts model
✔ removed the voice sytle for qwen 3 in the voice clone becuase it was not created for this purpose
✔ added the voice style input to the voice lab tool for the qwen3 tts model
✔ added search to the library input in the voice clone tool
✔ added sorting to the library input in the voice clone tool
✔ added search to the audio library
✔added sorting and other filtering options to the audio library
✔ added the analyze audio input feature into the voice lab tool
✔ many other various minor improvements
 
Fusion Scribe v1.0.0.8

✔ additional fixes to enhance the new ai engine builds
✔ improved qwen and omnivoice engines on new graphics cards in windows
✔ fixed other several issues for windows version
✔ fixed several issues for mac version
✔ many other internal fixes
 
Fusion Scribe v1.0.0.9

✔ fixed issue with voice speed control when using the ElevenLabs API option in the Voice Clone and Voice Lab tools
✔ several other various minor improvements
 
Fusion Scribe v1.0.1.0

✔ updated the ElevenLabs integration. you can now select models in the AI settings for ElevenLabs (Eleven v4, v4 Turbo, Multilingual v2, Flash v2.5, v3)
✔ Updated the ElevenLabs voices being used in all tools to get your accounts voices (premade, your clones, designed voices and Voice Library picks)
✔ ElevenLabs default model moved from the deprecated Turbo v2.5 to Flash v2.5 (same voices and settings)
✔ ElevenLabs speed, style and speaker boost controls are greyed out when an Eleven v3/v4 model is selected, since those models do not support them
✔ fixed Studio multi-speaker Import Document failing with 'No usable output' when OpenAI or Gemini is the AI provider
✔ OpenAI and Gemini AI requests now use their native chat endpoints, so AI Write and Studio import get the full output length and strict JSON mode
✔ fixed auto-assign voice styles not being applied for OpenAI, OpenRouter and Local AI during Studio import
✔ added a provider selector inside the Studio Import Document window so you can switch AI providers without leaving the import
✔ fixed Studio projects created from Import Document, AI Script or script import landing in All instead of the folder you were viewing
✔ improved Gemini voice generation reliability: lines that come back without audio are retried automatically, and the error now explains why
✔ other minor updates
 

User Menu