mrfakename PRO

mrfakename

TTS-AGI

·

https://mrfake.name/

AI & ML interests

LLMs, TTS, & Open Source

Recent Activity

updated a Space about 24 hours ago

TTS-AGI/speech-performance-arena

new activity 1 day ago

mrfakename/E2-F5-TTS:Tip for F5-TTS: The speed parameter is NOT a speed control, it's a signal compressor.

updated a Space 1 day ago

mrfakename/sov-transcribe-1

View all activity

Organizations

mrfakename 's Spaces 197

Flow

Node editor that wires Gradio Spaces into workflows

Dia - Text to Dialogue

Dia - 1.6B Text-to-Dialogue Model

MegaTTS 3 Voice Cloning

MegaTTS 3 but with voice cloning!

OpenDalle V1.1 GPU Demo

A demo of OpenDalle V1.1 on a ZERO GPU.

F5-TTS

F5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)

Z Image Turbo

Generate images from text prompts in seconds

MiniMax-H3 Ultra Fast

Ultra-fast local NVFP4 video + synchronized audio generation

SOV-Transcribe-1

Speech to text with style and context control

Evals ZONOS3-Mini

Evals ZONOS2

Evals Echo TTS

ZONOS3 Mini

Multilingual TTS with preset voices, cloning and moods

ZONOS3 Mini WebGPU

ZONOS3 Mini text to speech in your browser on WebGPU

P-JiT 21K

Text-to-image with Linum's 2B pixel-space DiT

Chroma H3

Text-to-image with lodestones' Chroma H3 stills model

Viggle Image Swap

Swap people in a picture with character-sheet characters

Novel Humanize 4B WebGPU

Humanize Chinese web fiction, in your browser

SenseNova Code2Video

Describe a short animation and watch it get made in code

Novel Humanize 4B

Make AI-sounding Chinese web fiction read human

SenseNova Loop 9B

Ask questions about text or a picture

Hemmingway-1.5

Writing that reads like a person wrote it

Nemotron 3.5 Transcribe

Speech to text in 40 languages, speakers and translation

LTX-2 Face Swap

Put a face from a photo into a short video with LTX-2

Phonon-2.5 English WebGPU

Phonon-2.5 English speech recognition in your browser