Skip to content

YOUR LOCAL AI VOICE STUDIO FOR MAC

Private, unlimited.Text-to-speech for Apple Silicon.

Murmur turns scripts into natural speech on your Mac, with voices you clone or design yourself.
One purchase, unlimited generation. Your audio never leaves the machine.

Cloning and Voice Design require 16 GB+ memory and extra model downloads.

macOS 15+ Apple Silicon On-device Unlimited generation 860+ community voices

Try Murmur’s voice studio

Model Kokoro
SCRIPTRecorded in Murmur

Some ideas start as a scribble. A sentence in your notes. A story you cannot stop thinking about. Give yours a voice.

117 characters

Recorded samples. Create your own in the Mac app.

Ready to play
↖   Press play. It's a real recording.

WHO USES MURMUR

YouTubers Podcasters Educators Indie developers Businesses
THE STUDIO, UP CLOSE

A whole studio.
Not a text box.

Your words. Your cast. Your final cut. Make a quick voiceover or build a longer production, in one native Mac workspace.

This is the actual app.
  1. 01 · Start with your scriptWrite or import the words.
  2. 02 · Make it sound like youChoose, clone, or design a voice.
  3. 03 · Finish your productionArrange clips. Export WAV or M4A.
Explore the interactive app tourRecorded demos, not live generation
MURMUR / UP CLOSEProjects

Actual Projects screenshot. Cropped to the native app window; the interface is unchanged.

THE COMMUNITY, IN YOUR STUDIO

860+community voices.
Find your sound.

A narrator for your next chapter. A character for your story. A different accent for your voiceover.

Listen to a few here, then use the same community library with your own scripts in Murmur.

Explore the voice libraryFree to browse & listen. Create in the Mac app.
MAKE IT YOURS

From this page
to your next project.

  1. 01
    Find the voice

    Open Explore Voices in Murmur and search its name.

  2. 02
    Click Use

    Download its reference and select a compatible cloning model.

  3. 03
    Add your words

    Enter your script and generate speech locally on your Mac.

Not all voices are bundled. Optional cloning models need 16 GB+ memory and additional downloads. Output varies by model; check voice permissions before use.

How to use community voices
VOICE DESIGN / FROM WORDS TO A VOICE

Meet your
next cast.

Describe a voice, preview it, and save it for your scripts. No reference recording needed. Hear a few designed voices below.

Explore Voice Design

Recorded demos · illustrative character artwork

  1. Voice Design demo
    Illustrative witch character in a bakery with floating pastries.
    Fantasy comedy

    Witch Bakery

    Raspy, playful, and just a little mischievous.

  2. Voice Design demo
    Illustrative radio operator character wearing a headset at a space-station console.
    Game dialogue

    Radio Operator

    Dry humor. Clipped delivery. Calm under pressure.

  3. Voice Design demo
    Illustrative documentary narrator character overlooking a misty valley.
    Documentary

    Field Narrator

    Soft authority and a warm, observational tone.

  4. Voice Design demo
    Illustrative spa robot character offering a towel beside candles.
    Wellness comedy

    Spa Robot

    Soothing, slow, and unintentionally literal.

Four voices. Different worlds.
THE AUDITION / Witch Bakery
The croissants are fresh, the curses are mild, and the gingerbread man has stopped screaming.
Read the voice direction

Female, elderly, raspy and playful, high theatrical energy, uneven pacing, mischievous tone, occasional cackling quality, suitable for fantasy comedy dialogue.

On the casting desk

Witch Bakery Owner
0:000:06

A recorded demo, not live generation.

Choose a character and press Listen to hear a recorded demo.

Recorded Voice Design demos, separate from the community library. Design voices in the Mac app with an optional model and 16 GB+ memory. Results and language support vary by model.

Compare languages & models
LOCAL BY DESIGN

Your Mac does the work.

No cloud generation bill. A few things to know before you start.

Built for Apple Silicon

macOS 15 or later on an M1 or newer Mac. Intel Macs aren’t supported.

Choose the right model

Start with bundled Kokoro. Optional models for cloning and Voice Design need 16 GB+ unified memory and extra downloads.

Generate offline after setup

Your scripts and generated audio stay local. Setup, license checks, community browsing, and updates use the internet.

Generation speed and storage needs vary by model and Mac. Local processing is not a promise of identical speed or quality across every model. Read setup details · Privacy details

FROM MURMUR CUSTOMERS

In their own words.

“Murmur is an excellent AI voice cloner, I use it a lot to make DJ jingles/drops”
Lucas Schmidt · excerpt
Read the full review

Murmur is an excellent AI voice cloner, I use it a lot to make DJ jingles/drops, and is even great for cloning your own voice if you can't be bothered to record yourself. I was recently disturbed that on a previous update there seemed to be a 30 second sample limit, thereby breaking all my voice models. For me that rendered it useless, as I really didn't want to have to start from scratch. I am very pleased to say that has now been fixed and Murmur is best in its class. All my models are now working once more. I thoroughly recommend it!

“Excellent customer service. Easy to use interface. The main model Fish-speech produces high quality audio results. Highly recommended.”
K. Kwatamani · April 11 update excerpt
Read the full review

We received a prompt response regarding our issue and look forward to the fully functioning fish-audio model. (Update April 11: Excellent customer service. Easy to use interface. The main model Fish-speech produces high quality audio results. Highly recommended.)

“Amazing app, incredible quality! And the best part is it is all offline!”
Murmur customer
A NOTE FROM THE MAKER

Hi, I’m Tarun.

I build Murmur. Questions about your Mac, help with a voice, or an idea for the app? You can email me directly.

YOUR LOCAL VOICE STUDIO

Make more.
Pay once.

From a single voiceover to your next audiobook. Keep the production on your Mac.

  • Unlimited local text-to-speech. No credits.
  • Voice cloning and Voice Design on supported Macs.
  • Projects, multi-speaker scripts, and a batch queue.
  • Export WAV or M4A for your next edit.

Cloning and Voice Design need 16 GB+ unified memory and optional model downloads.

ImageMurmur for Mac
$49USD · one-time purchase

One purchase. One license for one Mac.

Get Murmur — $49

Secure checkout with Polar · taxes shown at checkout.
Download and license key delivered by email.

7-day money-back guarantee

Check your Mac before buyingmacOS 15+ · Apple Silicon (M1 or newer).
16 GB+ for optional cloning and design models.
Intel Macs are not supported.

Not sure? Ask me before buying

Already purchased? Download for MacA purchased license is required. This is not a free trial.

BEFORE YOU BUY

A few good questions.

Still wondering? Talk to the maker.

What does one purchase include?

Murmur is $49 USD as a one-time purchase. One purchase. One license for one Mac. Generate locally without credits, per-word charges, or a monthly subscription. Applicable taxes are shown at checkout.

Will it work on my Mac?

You need macOS 15 or later and Apple Silicon (M1 or newer). Intel Macs are not supported. Kokoro handles basic narration on compatible Macs; optional models, including voice cloning and Voice Design, require at least 16 GB of unified memory. Speed and available features depend on the selected model and your hardware.

What do I need to download?

Kokoro is bundled for basic text-to-speech. Optional models for cloning, Voice Design, and other speech features require at least 16 GB of unified memory and additional model/runtime downloads. For example, the app estimates about 1.7 GB for Qwen3-TTS Base and 2.3–4.5 GB for Voice Design, depending on the variant. These are model downloads, not total installation sizes: allow additional free space for runtimes, setup, and generated audio. Total disk space needs and generation speed vary by model and your Mac.

Does it work without the internet?

Speech generation runs locally after setup, but periodic online license validation is still required. Internet is also needed for purchase, activation, optional model downloads, updates, and community voice browsing. Diagnostic connections are described in the Privacy Policy; local generation does not upload your scripts or generated audio. Read the Privacy Policy.

Can I use the audio in commercial projects?

Your Murmur purchase licenses the app. You must also follow the selected speech model’s license and have the rights and permissions needed for the script, reference recording, and voice. Community voices do not all come with the same permissions. Check those terms before publishing or doing client work. Read the usage terms.

What about updates or moving to a new Mac?

Your purchase includes perpetual access to the version you buy and free updates for that version. Future versions and upgrades are not guaranteed. One active Mac per license. To move to another Mac, the previous activation must be released. Contact support if you need help changing Macs.

What happens after I buy?

Your download and license key arrive by email. Install Murmur, activate your license, and start with the bundled Kokoro model. Add optional models for other workflows. The app download requires a purchased license; it is not a free trial. If Murmur does not fit your workflow, email your purchase receipt within 7 days to request a refund.

What does Apple notarization mean?

Apple notarization checks submitted software for malicious components. It is not an App Store review or an endorsement.