Clone a voice with Enhanced Text-to-Speech

Enhanced Text-to-Speech can build a custom voice from a short reference recording — a single clip of someone speaking — and then narrate your manuscript in that voice. The clone is created on your Mac, with no long training wait. This is a zero-shot clone: you don't supply hours of audio or wait for a model to retrain. You give Arqenne one short sample, and it does the rest.

Everything happens locally. The reference audio you provide and the cloned voice it produces stay on your Mac and are never uploaded.

Voice cloning is part of Enhanced Text-to-Speech, the studio-quality engine. It runs on the GPU (Metal) and requires an Apple Silicon Mac. For an overview of the built-in voices and the two TTS engines, see Using Text-to-Speech.

Before you start

You need:

An Apple Silicon Mac. Arqenne runs on Apple Silicon (M-series) Macs, and Enhanced Text-to-Speech — and therefore voice cloning — uses the GPU (Metal).
The Enhanced TTS model downloaded. Arqenne downloads this automatically the first time you use Enhanced Text-to-Speech. It's roughly 3.5 GB, so your first clone may pause while that download finishes. After that, cloning works offline. See Downloading & managing local models for where models live and how to check on a download.
A reference recording. A short clip — around 10 to 30 seconds — of the voice you want to clone. You can record one or import an existing WAV file.

Permission first. Only clone voices you have the right to use — your own voice, or someone who has clearly agreed to it. A cloned voice is a likeness; treat it like one.

How cloning works

The flow has three parts: you create a speaker and give it a reference recording, Arqenne builds the cloned voice from that recording, and then you assign the speaker to paragraphs and generate audio like any other voice.

Create a new speaker. In the manuscript editor, switch to Audio mode (using the Text / Audio toggle). Each paragraph becomes its own lane with a voice selector. Create a new speaker for your clone and give it a name you'll recognize.
Give it a reference recording. Provide the speaker with a short reference clip — either record one or import an existing WAV file. This recording is the entire basis for the clone, so its quality matters more than anything else (see Recording a good reference below).
Let Arqenne build the voice. From your reference, Arqenne builds the cloned voice on-device. There's no lengthy training step — the voice is ready to use right away.
Assign the speaker and generate. In Audio mode, set a paragraph's lane to your cloned speaker, then use Generate Audio to render that paragraph. Use Play All to play every rendered paragraph in order; the current paragraph is highlighted as it plays. As with any voice, edited paragraphs are flagged stale so you know to regenerate just those.

Recording a good reference

The clone can only be as good as the clip you give it. A few minutes spent on a clean reference recording pays off in every paragraph you generate afterward.

Aim for	Why it matters
Roughly 10–30 seconds	Long enough to capture the voice, short enough to stay consistent.
One speaker only	Background voices or overlapping speech confuse the clone. Keep it to a single person.
A quiet room	Minimal background noise, hum, or echo. Room reflections and fans bleed into the result.
Consistent tone and pace	Even volume and a steady rhythm give the clone a stable starting point.
The style you actually want	The clone mirrors how the reference is read. If you want a warm, unhurried narrator, record the reference that way.

A clean 15-second clip almost always beats a noisy 60-second one. When a clone sounds off, the reference is the first thing to improve.

Tuning the result

Once a clone is producing audio, you can adjust how it performs without re-recording. Each speaker carries its own settings, so you can tune the clone independently of the built-in voices.

Expressiveness — how animated or restrained the delivery is. Lower it for steady, even narration; raise it for more emotion and emphasis.
Speed / pacing — how quickly the voice reads. Nudge it slower for dramatic narration or faster for brisk dialogue.

Make a small change, regenerate a paragraph, and listen. Tuning is quick because generation is local — Enhanced TTS produces audio faster than real time on Apple Silicon, so you can iterate freely.

Privacy and responsible use

Nothing is uploaded. Your reference recording and the cloned voice it produces stay on your Mac. Cloning runs entirely on-device, and your text and audio never leave the machine.
Generated audio is yours. Clones produce the same 24 kHz WAV files as any other voice, saved alongside your project.
Only clone voices you're allowed to. Clone your own voice, or a voice whose owner has clearly agreed. Don't impersonate real people without permission.

Troubleshooting

The clone sounds off, robotic, or unlike the reference

Improve the reference recording first — it's the single biggest factor. Use a cleaner clip: less background noise, one speaker only, even tone and pace. If your reference is very short, try one closer to 20–30 seconds. Then point the speaker at the better recording and regenerate.

Voice cloning isn't available

Cloning is part of Enhanced Text-to-Speech, which becomes available once its model (~3.5 GB) has finished downloading. If cloning is greyed out, check that the download has completed — see Downloading & managing local models. The Standard Text-to-Speech voices work in the meantime.

The first clone is taking a long time

Your first use of Enhanced Text-to-Speech downloads its model (~3.5 GB). Until that finishes, cloning and Enhanced generation will wait. Once the download completes, it's cached and you won't wait again. To check on a download in progress, see Downloading & managing local models.

Where the model lives

If you want to confirm the Enhanced TTS model is present, models are stored under:

~/Library/Application Support/com.arqenne.studio/models/

The Standard Text-to-Speech engine and its starter voices live under a separate tts/ subfolder of the same com.arqenne.studio/ directory.