Vibing — Just Speak It!

Powered by VibeVoice
More thanyour intelligent voice input method, but alsoyour intention expression assistant, andyour interface to the AI-native world.
Download for Mac Download for Windows GitHub

How to Use

MacHold Right ⌥ Option
WindowsHold Ctrl + Win
Recognizing...
I want you to first import torch and configure the CUDA device, then define the transformer model with eight heads...
Mac
~
1
2
3
4
5
6
7
8
9
0
-
=
del
tab
Q
W
E
R
T
Y
U
I
O
P
[
]
\
caps
A
S
D
F
G
H
J
K
L
;
'
return
shift
Z
X
C
V
B
N
M
,
.
/
shift
fn
⌃
⌥
⌘
⌘
⌥
←
↑↓
→
Windows
~
1
2
3
4
5
6
7
8
9
0
-
=
Bksp
Tab
Q
W
E
R
T
Y
U
I
O
P
[
]
\
Caps
A
S
D
F
G
H
J
K
L
;
'
Enter
Shift
Z
X
C
V
B
N
M
,
.
/
Shift
Ctrl
Win
Alt
Alt
Win
Menu
Ctrl

Video Introduction

Key Features

Long-Form Voice Input

Over 5 minutes of continuous speech in a single recording.

Personalized Hotwords

Custom vocabulary for names, jargon, and domain-specific terms.

Context-Aware Intent Understanding

Understands what you mean, not just what you say.

Multilingual

Speak in any of 50+ languages with automatic detection.

Mixed-Language Input

Switch between languages freely within a single sentence.

LLM-Powered Rewriting

AI rewrites your speech into polished, context-appropriate text.

Translation

Real-time voice translation across languages.

Works Everywhere You Type

Vibe Coding

src
train.py
model.py
dataset.py
configs
config.yaml
# Training Pipeline import torch import torch.nn as nn from torch.utils.data import DataLoader from model import VoiceTransformer device = torch.device("cuda" if torch.cuda.is_available() else "cpu") model = VoiceTransformer(d_model=512, nhead=8) model.to(device) optimizer = torch.optim.AdamW(model.parameters(), lr=3e-4)
✨ Claude Code ~/project
>
Listening...
Recognizing...
Vibing…
Done

Presentation

Q1 Business Review
FY2026 · Quarterly Performance
Revenue grew 23% YoY

Q1 Business Review

FY2026 · Quarterly Performance

Revenue grew 23% year over year

Listening...
Recognizing...
Vibing…
Done

Document

HomeInsertDesignLayoutReferencesReview

Q1 Product Planning — Meeting Notes

Date: March 25, 2026
Attendees: Product, Engineering, Design

1. Core Objectives
This quarter we focus on cross-platform voice input,
ensuring seamless typing across VS Code, Office, and
presentation environments.

2. Key Decisions

Listening...
Recognizing...
Vibing…
Done

Chat & Message

💬
👥
📅
📁
Engineering
general
voice-engine
frontend
releases
# general
A
Alice Chen10:32 AM
新的语音引擎通过了所有集成测试，可以开始 review 了！
B
Bob Kim10:45 AM
太好了！下午我来看 PR，有没有 breaking changes？
Y
YouNow
Type a message...
Recording (Translate)
Recognizing...
Translating…
Done