Lordz Ai

kokoro voice studio

Engine Kokoro v1 Quality Q8 Runtime — Match checking…

Voice Source Mix two voices

Voice A

Voice B

Mix

A B 0.00

Speed

1.00x

Idle.

Voice Presets One-click recipes

Sweet Kid · F

Brit Hybrid · F

Soft Whisper · F

Buddy · M

Cheeky · M

Brit Gent · M

Androgyne · X

Extreme A · F

Match Voice Find closest Kokoro voice

Sample

Upload a clean 5–15s clip

Browser mode uses on-device fingerprinting (pitch + brightness + timbre). For higher fidelity, run the local server at 127.0.0.1:7860.

Quality preset Model precision

StudioFP16 · 155MB

BalancedQ8 · 83MB

LiteQ4 · 42MB

MobileQ4F16 · 47MB

Cached after first download. Switch any time to re-download at chosen quality.

Composer Type and generate

Quick Guide

Length CPU GPU

~300 chars ~15s ~3s

~800 chars ~45s ~10s

~2000 chars ~3 min ~30s

🎬 Reels → Generate A/B
🎙 Narration → ⚡ Stream
📖 Long content → Stream + join in CapCut

Length	CPU	GPU
~300 chars	~15s	~3s
~800 chars	~45s	~10s
~2000 chars	~3 min	~30s

71 / 1,200 chars · est. ~instant

Save ▾

Recipe ▾

🎧 Preview · 10 sec · Upgrade to download ↗

Style & Effects

DSP preset

RawNo DSP

PolishedStandard

PremiumWarmth + double

Pro PackAll tricks

Emotion

None

Polish

Cartoon

Hero

Happy

Sad

Whisper

Cinematic

Angry

Calm

Intensity 100%

Reference style

None

Excited

Gentle

Dramatic

Cheerful

Intensity 100%

Voice Sampling Per-render shaping

Stability

Expressive Consistent 0.50

Style

Natural Boost 0.00

Soft

Off Whisper 0.00

Pro Tricks Studio-grade processing

📈 Pitch contourRise on ?, fall on . 🎤 Best take3-take cleanest pick 🏠 Room toneSubtle ambient -48dB 🏷 SSML markupbreak/emphasis 📡 Pre-emphasisBroadcast clarity

Advanced DSP & Inline Markup

DSP overrides

🧠 Smart textNumbers/abbrev expand 🎚 De-EsserRemove sibilance 📐 MultibandSmooth all freqs 🌫 Tape warmthAnalog harmonics 🎙 Voice doubleADT chorus ⏸ Sentence pausesNatural silence 🔊 LUFS normBroadcast loudness 📈 Upsample 44.1kStudio rate

Inline markup

*emphasis*Word renders 22% slower

[voice:af_heart]Switch voice mid-text

[happy] [sad] [whisper]Per-chunk emotion

<break time="500ms"/>SSML silence

<emphasis>word</emphasis>SSML stress

<prosody rate="slow">SSML rate

Lordz Ai

Composer Type and generate

Quick Guide

Length CPU GPU

~300 chars ~15s ~3s

~800 chars ~45s ~10s

~2000 chars ~3 min ~30s

🎬 Reels → Generate A/B
🎙 Narration → ⚡ Stream
📖 Long content → Stream + join in CapCut

Style & Effects

Voice Sampling Per-render shaping

Pro Tricks Studio-grade processing

AI Match Find a Kokoro voice that matches a sample

Voice Library Browse, rate & tag your saved voices

Composer Type and generate ℹ Quick Guide LengthCPUGPU ~300 chars~15s~3s ~800 chars~45s~10s ~2000 chars~3 min~30s 🎬 Reels → Generate A/B 🎙 Narration → ⚡ Stream 📖 Long content → Stream + join in CapCut

Style & Effects

Voice Sampling Per-render shaping

Pro Tricks Studio-grade processing

AI Match Find a Kokoro voice that matches a sample

Voice Library Browse, rate & tag your saved voices

Composer Type and generate

Quick Guide

Length CPU GPU

~300 chars ~15s ~3s

~800 chars ~45s ~10s

~2000 chars ~3 min ~30s

🎬 Reels → Generate A/B
🎙 Narration → ⚡ Stream
📖 Long content → Stream + join in CapCut