MyLosen Voice Studio | Zero-Shot Voice Cloning & TTS

MyLosen Voice Studio

Zero-Shot Voice Cloning & Speech AI

recep_voice (Ga.m4a)

Speech Synthesizer

Audio8 ONNX Engine

Select Cloned Voice Profile

Text Prompt to Synthesize

Quick Presets:

00:00 / 00:00

Synthesis Tuning

Temperature 0.3

Top P 0.9

Random Seed

CURRENT PIPELINE

• TTS Model: ArkTTS ONNX

• Voice Reference: Ga.m4a

• Sample Rate: 44,100 Hz

Zero-Shot Voice Cloner

Voice Profile Name

Reference Audio File

Click or Drag & Drop Reference Audio

Default: Ga.m4a (Click to pick a new file)

Reference Transcript (Spoken Text)

Registered Voices

recep_voice

Source: Ga.m4a (44.1kHz)

Active

Shortinator AI Automated Pipeline

Automated YouTube Shorts

ACTIVE LLM MODEL

Gemma 4 (gemma4)

Loaded via local Ollama engine

CLONED VOICE PROFILE

recep_voice

Source Audio: Ga.m4a

DAILY UPLOAD BATCH

1 Short / Run

n8n Workflow Execution

AUTOMATED YOUTUBE UPLOAD SCHEDULE (5 DAILY RUNS)

07:30 AM

12:30 PM

16:30 PM

19:00 PM

22:00 PM