Text-to-speech generation
Generate audio from text using the site’s text-to-speech workflow. The pricing page says generation is unlimited on all listed plans, with audio length limits varying by plan.
FakeYou
ClaimFakeYou is an AI voice and video generator for text-to-speech and voice-to-voice conversion, with free core features, premium tiers, and custom voice models.
Overview
FakeYou is an AI voice and video generator focused on turning text or speech into character-style audio. The home page highlights text-to-speech, voice-to-voice, and voice design tools, while the site also points to video creation and model contribution workflows.
The product positions itself as a creative tool for generating voices and videos, with a guide aimed at improving output quality and a contribution area for users who want to upload models, weights, or workflows. The about page says FakeYou is one component of a broader set of production and creative tooling.
Features
Voice-to-voice conversion
Convert speech into another voice through the voice-to-voice workflow. Paid plans raise the maximum audio duration and add private-model upload options.
Voice Designer
Create your own AI voice through the Voice Designer area. The site presents this as a separate tool alongside TTS and voice-to-voice.
TTS guidance for better output
Follow the guide’s practical tips for pronunciation and pacing, including punctuation, commas, spelling variations, and emotional conditioning.
Model and workflow contributions
Contribute new models and workflows, including TTS voices, vocoders, Stable Diffusion weights, LoRA weights, and workflow submissions.
Premium processing tiers
Use premium plans to increase processing priority and unlock longer audio limits, with the highest listed tier adding private-model sharing.
Use Cases
Generate character-style narration
Turn written lines into spoken audio using the TTS workflow, then refine the result with punctuation, spelling variations, or emotional lead-in text when pronunciation needs help.
Convert one voice into another
Recast existing speech into another voice using the voice-to-voice tool. This fits quick voice transformations where the goal is a different vocal style rather than a new script.
Create or contribute voice models
Build a custom voice asset with Voice Designer or by contributing a new model, weight, or workflow, which is useful for creators who want more control over the available voices.
Work with longer or higher-priority jobs
Use premium plans when you need faster processing, longer audio output, or private model uploads. The plan comparison is centered on workflow limits rather than full platform access.
Prototype audio and video content
Explore the site’s video-related tooling and ArtCraft promotion alongside the voice tools when you are assembling AI-assisted creative content across audio and video.
Pros and Cons
Pros
- Offers text-to-speech, voice-to-voice, and voice design in one product.
- Provides free access to core features, with paid plans for faster processing and higher limits.
- Includes practical guidance for improving pronunciation and phrasing.
- Supports community contributions such as new voice models and workflows.
- Documents premium plan differences clearly on the pricing page.
Cons
- The source does not provide detailed information about video workflow limits or export options.
- Some guidance on output quality is model-dependent and may require manual tuning of punctuation, spelling, or emotional cues.
FAQ
Is FakeYou free to use?
Yes. The pricing page says FakeYou’s features are free to use, with premium plans for faster processing and higher output limits.
How do you improve TTS output quality?
The guide recommends adding punctuation, commas, misspellings, or emotional lead-in text to improve pronunciation and pacing. It also notes that some models support Arpabet phonetic annotation.
What can I do with FakeYou?
The source highlights text-to-speech, voice-to-voice, and voice design. The site also references video generation and video templates, but the most concrete workflows shown are audio generation and model uploads.
Can users contribute their own models?
The contribute page says users can upload new TTS voice models, voice-to-voice weights, vocoders, Stable Diffusion weights, LoRA weights, workflows, and suggested categories.
Quick Facts
- Category
- AI voice generator
- Primary workflows
- Text to speech, voice to voice, voice design
- Pricing model
- Free core features; paid Plus, Pro, and Elite plans
- Source domain
- fakeyou.com
- About page summary
- Built as part of a broader set of production and creative tooling
- Community contribution
- Supports uploads for models, weights, workflows, and categories