Skip to content
PowerBeefPublic

About

Vocello: a private voice studio for Apple Silicon. Write a script, pick or describe a voice, and generate speech locally on your Mac and iPhone. Native Swift and MLX, no Python, no cloud. Mac app and command line out now, iPhone beta on TestFlight. (Formerly QwenVoice.)

Topics

Resources

Contributing

Security policy

Stars

388 stars

Watchers

5 watching

Forks

Repository files navigation

What is Vocello

Vocello is a voice studio for your Mac and iPhone. Write a script, choose a voice, and Vocello speaks it with Qwen3-TTS, an open text-to-speech model, running on your own Apple Silicon.

There is no account, no credits and no cloud. Your scripts, recordings, voices and takes stay on your device unless you export them.

The Vocello Studio on a Mac: a script in the editor, the Aiden voice with a Calm delivery in English, and a Built-in Voice take playing in the inline player.

What it does

Three ways to make a voice. Built-in Voice: nine natural voices in ten languages, in the delivery you ask for. Voice Design: describe a voice in plain words and keep the ones you like. Voice Cloning: a new voice from a short clip of a voice you own or have permission to use.
  • Built-in Voice. Nine voices in ten languages, with a delivery preset (calm, whisper, happy and more) or a few words of your own about how it should sound.
  • Voice Design. Describe a voice, such as "a warm, clear narrator with a gentle British accent", hear it, and save the ones you like.
  • Voice Cloning. Record or import a short clip of a voice you own or have permission to use. Voice Cloning follows the reference voice, so the clip sets its character, and it waits for your consent in Settings.
Made for real projects: long scripts that play while they generate, ten languages detected from your script, saved voices, a searchable History kept on your device, every take marked as AI-generated with an inaudible AudioSeal watermark, no account or cloud, a command line with JSON output and an MCP server for AI agents, and signed, self-installing updates.

Vocello speaks Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish and Italian, and its interface comes in ten languages too, set apart from the speech language. Paste a whole chapter and it plans the script into segments that play one after another while the rest generates, then joins them into one file.

The delivery menu of Built-in Voice: distinct deliveries (Neutral, Sad, Calm, Whisper), directional hints (Happy, Angry, Fearful, Surprised) and Custom. Voice Design in the Studio, with the description A warm, clear narrator ready to generate.
Voice Cloning in the Studio, with a saved Studio narrator voice and the reminder to use permitted clips only. History, filtered by mode, listing Built-in Voice and Voice Design takes with their voice, date and length.

How it performs

Vocello 3.1 on a Mac mini M6 with 16 GB: about 19 seconds to make one minute of speech, 0.2 to 0.4 seconds until the first audio is ready, and 2.5 to 4.2 GB of peak memory while it speaks.

Once its model is loaded, Vocello makes speech about three times faster than you can listen to it, in every mode and at every script length, and a long script starts playing while the rest is still being made.

Bar chart: warm real-time factor of the Vocello 3.1 models by script length, lower is faster: Built-in Voice 0.30 to 0.36, Voice Design 0.29 to 0.34, Voice Cloning 0.30 to 0.41. Every bar sits below the real-time line at 1.0.

The real-time factor is the time it takes to generate one second of audio: at 0.30, a ten-second line takes three seconds. Each bar is the median of the warm takes in the latest benchmark records of the released build, on the benchmark Mac mini M6 (16 GB). The images in this section are regenerated from those records, so the numbers cannot drift from the evidence. → Benchmark history · How it is measured

Install and requirements

On a Mac. Download Vocello, drag it to Applications and open it. Then open Settings > Models & Files and download the model of each mode you want to use.

On iPhone. Join the public beta on TestFlight. The beta still runs Vocello 3.0; the 3.1 update follows there.

In Terminal. Install the signed command-line package, which asks for an administrator password. From a new Terminal window, check it, download the Built-in Voice model (its id still says speed, a name kept from earlier versions) and play a first take:

vocello --version
vocello models install pro_custom_speed
vocello custom --text "The train left at dawn." --play

vocello shares the Mac app's models, saved voices, settings and History, and answers in JSON for scripts. To let Claude Code speak through Vocello's MCP server:

claude mcp add --scope user vocello -- /usr/local/bin/vocello mcp
Platform Requirements Models
Mac macOS 26.0 or newer, Apple Silicon, 8 GB of memory (16 GB or more recommended for long projects) One model per mode
Command line macOS 26.0 or newer, Apple Silicon Shared with the Mac app
iPhone iPhone 15 Pro or newer, iOS 26.0 or newer One model per mode

Models are never bundled. Each mode's model downloads once from Hugging Face, about 2.2 GB, and is verified before it is used. → What's new in 3.1.0 · CLI reference · All releases

Settings, Models and Files: the Built-in Voice, Voice Design and Voice Cloning models, 1.7B parameters each, all ready.

Upgrading, and older Macs

History, saved voices and settings carry over from any earlier version. From 3.0, choose Vocello > Check for Updates; from 2.x, install the new DMG by hand once. Vocello then replaces the models you had with the new one for each mode, on its own on an unmetered network (about 4.7 GB for all three modes; Not Now stops it). The release notes have the details.

Vocello was called QwenVoice before 2.2.0, and old repository links redirect here. Macs on macOS 15 can use the legacy QwenVoice 1.2.3.

Note

Take quality is checked by machine, not by human listening. Automated checks catch gross failures (silence, a cut-off take, missing words, the wrong language), so a take can still carry a subtle defect, such as a swallowed syllable or a delivery that misses the requested style. Generate again for a different take. The release notes list the known limitations.

Under the hood

Vocello runs a 1.7-billion-parameter text-to-speech model natively on Apple Silicon: Swift 6 with strict concurrency, a first-party MLX runtime, and audio that streams with bounded memory. There is no Python, no server and no separate engine process.

How Vocello works: the Mac app, the iPhone app and the vocello command line each host the same engine in-process. The engine store admits a take and owns cancellation and memory policy. The VocelloQwen3Engine actor runs the talker, the code predictor and the speech decoder on MLX and Metal. Audio streams chunk by chunk through a limiter, an atomic WAV writer, an AudioSeal watermark and an audio check before it reaches History.

One engine serves all three hosts. The talker turns your script into codec frames, the code predictor fills in each frame, and the speech decoder turns them into 24 kHz audio that streams, chunk by chunk, to the player and through a limiter, an atomic WAV writer, a watermark and an audio check. A take reaches History only when all of that has finished. → Architecture

Vocello by the numbers: 1.7 billion parameters in each mode's model; 8-bit attention layers on a 4-bit model; about 36,000 upstream lines removed from the owned runtime; 24 kHz mono audio from a native decoder; Swift 6 strict concurrency, with actors owning the engine; no Python at runtime.
An owned runtime, not a Python wrapper. VocelloQwen3Core is derived from mlx-audio-swift v0.1.2 and narrowed to what Vocello ships: about 36,000 of its 49,000 upstream lines removed, every remaining file tracked with its change, and a facade that keeps raw MLX types out of the apps.
One model per mode, tuned where it counts. Each mode runs a single mixed-precision model: 4-bit weights, with the talker's attention layers at 8 bits, where extra precision bought the most for the least weight. It was chosen by automated screens whose decision rules were written down before their takes were generated. → How the model was chosen
Streaming that doesn't grow. Audio crosses an actor-owned, frame-bounded channel that never drops audio and suspends the producer instead of buffering, so the audio in flight is bounded by the channel, not by the length of the script.
Launch-bound, not compute-bound. Fusing the code predictor's rotary embedding removed about 600 kernel launches per frame (26% faster warm), and compiling the per-frame predictor pass added another 8 to 11% with byte-identical output. → Optimization ledger
Reproducible by construction. Every request carries its own seed and sampler state. Cancellation is typed and awaited, so a cancelled take never reaches History, and MLX errors arrive as typed failures instead of aborting the process.
Proof before merge. Fixed-seed byte identity gates every scheduling change, published benchmarks are pass-only, privacy-checked records, and UI tests drive the real Mac app and a paired iPhone, never a Simulator.

Build from source

You need full Xcode on an Apple Silicon Mac with macOS 26 or newer; New Mac setup lists the pinned tools.

git clone https://github.com/PowerBeef/Vocello.git
cd Vocello
./scripts/regenerate_project.sh
./scripts/build.sh build

project.yml generates the Xcode project, and the repository scripts are the build and test interface: scripts/dev.sh check runs the lint, contracts and tests your change touches. Start with CONTRIBUTING.md.

→ Architecture · CLI reference · Benchmarks · Testing runbook · Release notes · Roadmap

License and acknowledgements

Vocello is available under the MIT License. It builds on Qwen3-TTS, MLX, mlx-audio-swift and GRDB.swift. Third-party models and assets keep their own terms; see the third-party attributions and the runtime's notices.


The Vocello app icon
Vocello · private text to speech for your Mac and iPhone

About

Vocello: a private voice studio for Apple Silicon. Write a script, pick or describe a voice, and generate speech locally on your Mac and iPhone. Native Swift and MLX, no Python, no cloud. Mac app and command line out now, iPhone beta on TestFlight. (Formerly QwenVoice.)

Topics

Resources

Contributing

Security policy

Stars

388 stars

Watchers

5 watching

Forks

Releases

Packages

Used by

Contributors

Languages