GLOAM.FM
VOICE STUDIO
Features Models Intelligence Voice Lab Developers Docs Changelog Pricing Download
DOCUMENTATION

Getting started

Install Gloam Voice Studio, clone your first voice, and drive it programmatically through the local API. Everything runs on your Mac.

Requirements

Gloam Voice Studio is a native macOS app for Apple Silicon. You'll need:

macOS 14 (Sonoma) or newer
Apple Silicon — M1 / M2 / M3 / M4 (Intel Macs are not supported)
Disk space for model weights — from ~1 GB up to ~18 GB per model

Install

Download the latest signed build from GitHub Releases, unzip, and drag Gloam Voice Studio.app into /Applications. On first launch, pick a synthesis model and it downloads in-app with a storage preflight.

→ github.com/TinyTrashLabs/gloam-voice-studio/releases
SOON
Coming soon to the Mac App Store
One-click install and automatic updates — the same free, MIT-licensed app. Direct download stays available too.

Build from source

Prefer to build it yourself? You'll need Xcode 16+ and xcodegen.

# install the project generator brew install xcodegen # generate the Xcode project xcodegen generate # build Release xcodebuild build -project GloamVoiceStudio.xcodeproj \ -scheme GloamVoiceStudio -configuration Release \ -destination 'platform=macOS' -derivedDataPath build-app \ CODE_SIGN_IDENTITY=- # run it open build-app/Build/Products/Release/GloamVoiceStudio.app

The underlying EngineKit and StudioKit packages ship unit tests — run swift test.

Your first voice

Cloning a voice takes one reference clip:

1. Add a reference. Record directly in the app or drop an audio file. Reference clips auto-transcribe on-device — an optional transcript hint improves quality.

2. Name & save. The voice is saved to your library as a folder containing meta.json and ref.wav.

3. Generate. Type a line in the Studio editor, choose a backend, and synthesize. Generate two A/B takes to compare waveforms side-by-side.

Emotion & speed

Every take can be directed with one of five emotion variants and a playback speed from 0.5× to 2.0×.

flat neutral warm excited hype

For capable backends, per-session direction overrides let you drive temperature (Fish S2-Pro) or exaggeration (Chatterbox) directly, overriding the emotion preset.

Voice Lab scripts

Voice Lab is a multi-line script editor. Each line carries its own voice and emotion direction, and lines can be reordered at will.

Batch & stitch

Generate every line in a session serially with one click — per-line status runs queued → generating → done. Export the whole script as one WAV: the starred (or newest) take per line, a configurable silence gap between lines, and optional peak normalization to −0.18 dBFS.

Choosing a model

Swap synthesis backends per take. As a rough guide:

MODELRTFUSE WHEN
Chatterbox~2–3×Fast iterations
Chatterbox-Turbo~1–2×Best balance
Fish S2-Pro~1×Final masters
Qwen3-TTSvariesMultilingual / design

The Qwen3-TTS family also supports inventing a voice from a natural-language description (qwen3-design) and directing a preset speaker with instructions (qwen3-custom).

Local API server

Enable the optional HTTP server in Settings to drive synthesis programmatically. It binds to localhost only, on port 8790 by default, and speaks an OpenAI-compatible surface.

$ curl localhost:8790/v1/audio/speech \ -H 'content-type: application/json' \ -d '{ "voice": "my-voice", "input": "You'"'"'re locked in to Gloam FM.", "emotion": "hype", "speed": 1.0 }' -o out.wav → 200 OK · audio/wav

Because it's OpenAI-compatible, the server can both drive and be driven by the Python sibling project gloam-voice-engine.

.gvoice packs

Voices are portable. A .gvoice pack is a ZIP archive containing meta.json and ref.wav — the shared interchange format between the macOS app and the Python engine.

Export a voice from the studio and import it into gloam-voice-engine, or vice versa. Perfect for shipping your Gloam.fm DJ voices between environments.

Data & storage

Everything lives inside the macOS sandbox container. Nothing is uploaded or synced.

~/Library/Application Support/Gloam Voice Studio/ Voices/ # one folder per voice (meta.json + ref.wav) History/ # generated clips + metadata ~/Library/Caches/Models/ chatterbox/ chatterbox-turbo/ fish-s2-pro/ llm-*/

Shortcuts

Transcribe an audio file⇧ ⌘ T
Dictate into any editorDictate button
Ready to start?
Download the app and clone your first voice.
Download for macOS