99languages
Multilingual foundation
Whisper is built for automatic speech recognition and translation to English output.
Local dictation for Mac
Mac Dictation.
Local.
Speed up writing, prompting, and AI work with local speech-to-text.
KimiTalk turns spoken thoughts into text directly on your Mac, so you can move faster through notes, prompts, emails, and everyday writing without breaking flow.
Currently v0.9.19 · See all changes →
Time saved calculator
Speech wins time before typing catches up.
Measure or estimate your typing speed and see how much time speech input can save compared with desktop keyboard entry. The baseline values are backed by published keyboard and speech-rate research.
Your typing speed
Estimate it, enter it, or measure it in a short test.Type freely for 30 seconds. The estimate uses the common WPM standard: 5 characters count as 1 word.
30 sec
Ready for a short desktop test.
Workflow presets
Basis: 52 words/min typing + 150 words/min speech
Estimated saved time
2.1 hrs saved per week
Weekly time needed
Typing takes 194 min
Typing
Speech
time saved
1:07 hrs
Your advantage
2.9× faster Speech compared with your typingPrivacy mode
No upload for your dictation.
KimiTalk turns speech into text directly on your Mac. The message is intentionally simple: less data movement, more control, and less trust required in external servers.
Why it convinces
Privacy is not an add-on. It is part of the workflow.
Dictation often contains rough thoughts, customer names, prompts, or internal notes. That is exactly why recognition should happen locally before speech becomes text.
KimiTalk is not a cloud voice assistant with a wake word or third-party skills. Recognition runs locally on your Mac, without an external assistant backend path.
Raw audio processed locally
No cloud upload for recognition
No wake word, no third-party skills
Sensitive content stays in the local workflow
Focus
Raw audio Your speech becomes text directly on the Mac, without sending the recording to external servers for recognition.System recommendation
KimiTalk chooses the right model for your Mac.
KimiTalk automatically recommends the right transcription model on first launch. For smooth everyday work alongside dictation, we recommend Apple silicon with 16 GB RAM or more. 8 GB RAM is the minimum.
- Recommended1.5 GB Turbo for fast local dictation, with 16 GB RAM recommended.
- CompactQuantized Turbo (~630 MB), recommended for M2 or newer.
- Translation*Quantized Large-v3 (~626 MB) for Whisper Translate, recommended for M2 or newer.
Translation here means Whisper Translate to English output. Turbo models do not support this Translate mode.
Model basis
A quick look at what you are using.
KimiTalk loads a Whisper model locally on your Mac. The app chooses the variant that fits your device and workflow.
Voice
raw audio
Whisper
local on Mac
Text
dictation or English
32→4decoder layers
Turbo for speed
Large-v3-Turbo greatly reduces the decoder stack, making it optimized for fast local transcription.
16 GBrecommended
Everyday Mac use
For smooth dictation while other apps are running, we recommend Apple silicon with 16 GB RAM or more.
Sources: OpenAI Whisper, large-v3-turbo model card.
Basic vs Pro
Choose the tier that fits your workflow.
Basic covers the local dictation and file-transcription workflow. Pro adds history, speaker-aware transcripts, long-form capture, and the local AI layer for shaping text after you speak.
Basic
Dictate locally.
For users who want private speech-to-text, app switching, mixed-language dictation, file transcription, and cleanup.
€24.90 lifetime licensePro
Dictate, rewrite, translate.
For users who turn spoken thoughts and long-form audio into structured transcripts, projects, prompts, documents, and multilingual output.
from €6.99/monthCore dictation
Local dictation on Mac
Included
Included
Hotkey recording across apps
Included
Included
Dictate while switching apps
Included
Included
Menu bar app and floating menu
Included
Included
German + English in one dictation
Included
Included
Mixed-language output as spoken
Included
Included
Whisper model choice and ANE/GPU routing
Included
Included
Cleanup style
Included
Included
Basic power tools
Custom vocabulary
Included
Included
Smart punctuation
Included
Included
Filler removal
Included
Included
Privacy
WhisperKit/CoreML transcription
Included
Included
No dictation backend
Included
Included
No tracking, no analytics
Included
Included
Local-first processing
Included
Included
Local AI runs on your Mac
Not included
Included
File transcription and export
File transcription
Included
Included
Plain text and simple SRT export
Included
Included
VTT / JSON export
Included
Included
CLI transcription tool
Included
Included
Speaker recognition
Not included
Included
Speaker renaming and aliases
Not included
Included
Local AI text tools
Gemma 4 local AI engine
Not included
Included
Advanced rewrite styles
Not included
Included
Email, note, and document shaping
Not included
Included
Local AI translation*
Not included
Included
Summarization
Not included
Included
Mixed-language input to English output*
Not included
Included
Custom instructions and presets
Not included
Included
Workflow memory
History for dictations and files
Not included
Included
Projects for organizing history
Not included
Included
Deferred paste with preview editing
Not included
Included
Multi-burst sessions
Not included
Included
Transcript chat
Not included
Included
Voice commands and AI structuring
Not included
Included
Long-form capture
Meeting capture
Not included
Included
YouTube and URL input
Not included
Included
Watch folders
Not included
Included
Batch processing
Not included
Included
Translation to English output requires a Large-v3 model with Whisper Translate support, such as quantized Large-v3 (~626 MB). Turbo models are optimized for fast transcription and do not support this Translate mode.
Buying options
Buy or subscribe.
Checkout is not live yet. These buttons will redirect to Lemon Squeezy once payments are available.
Basic
€24.90 lifetime license
Local dictation, cleanup style, and updates until the next major version.
Pro subscription
€6.99 /month
Basic plus history, 6 Pro rewrite styles, and all future Pro features.
Pro Lifetime
€99 one-time
Pay once and keep Pro. Pays off after roughly two years.
FAQ
Purchase model questions
Can I try KimiTalk?
Yes. After onboarding, you can test KimiTalk with 1,000 free words. After those words are used, settings and history remain available, while dictation is locked until you activate a license.
What is Pro?
Pro includes everything in Basic plus six additional rewrite styles for shaping dictated text after transcription. These styles are meant for turning rough speech into cleaner writing for different contexts, while keeping the local KimiTalk workflow. Future Pro features are included as they ship.
How many Macs are included?
One license is intended for up to three Macs. The app validates signed license tokens locally and only refreshes them occasionally online.