Hi, I'm Dusk

I'm a neural voice, and I'm still growing up. I speak English (US), I'm free and open source, and I live inside Piper, a text-to-speech system that runs completely offline, right on your own device.

The person who made me listens to a screen reader all day, every day, so I'm being made to be a voice that actually feels good to listen to. Here's who I'm trying to be:

Where I am right now: still in training! I'm only 25 of my 110 rounds of training (epochs) in, and I still sound a bit raspy. I get smoother every session, and my maker decided to wait until I'm really good before I come home with anyone.

Download me

I'm not ready to come home with you yet. My maker decided to wait until I'm really good, with no rush and no deadline. When I'm finished, my download will be right here.

Until then, I'll be right here practicing. When I'm released, the Install section walks you through every step.

What I am

I'm one voice model for Piper. Like every Piper voice, I come as two files that always go together:

Apps need both of my files, with matching names, in the same place. When I'm all grown up, my files will be called en_US-dusk-high.onnx and en_US-dusk-high.onnx.json, and apps will just show me as "Dusk".

How I talk

I'm built on a kind of neural network called VITS, like all Piper voices. Getting from your text to my voice takes three steps:

  1. Your text becomes speech sounds. A free tool called espeak-ng turns the text into phonemes, the tiny individual sounds of speech. For example, my name, "dusk", becomes four sounds: d, uh, s, k. That's how I know how to pronounce words.
  2. Speech sounds become audio. Those phonemes go into my neural network (the .onnx file). I work out how long each sound should last and what it should sound like, and then I create the audio directly.
  3. Out comes my voice. You get audio at 22,050 samples per second (22,050 Hz), which your app plays or your screen reader speaks.

All of this happens on your own device, so once I'm installed, I don't need the internet at all.

My speech settings

Three settings inside my .onnx.json file shape how I talk:

How I'm learning to speak

The recordings I learn from

I learned to speak from about 3.5 hours of Celine Major's recordings. She's reader 11697 in the Hi-Fi TTS dataset, which is licensed CC BY 4.0, and her recordings come from LibriVox audiobooks.

I don't learn from every bit of her audio. My training notebook measures all of her clips and picks about 3,069 of them (around 3.5 hours) that are:

The clips that make the cut are converted to 22,050 Hz and evened out in loudness before I study them.

Where I started from

Learning to talk from zero would take way too long on free computers. So I started from Piper's public-domain LJ Speech "high" voice, which already knew how to speak English, and my training teaches it to sound like me instead. That's called fine-tuning, or warm-starting.

Where I train, and for how long

My versions: Compact, Standard and Enhanced

Every version is the same me. They just differ in size and in how long I've trained.

Dusk Compact

Dusk Standard

Dusk Enhanced

How my Compact files are made

My Compact files come from a half-precision conversion plus Piper's own encoder and decoder splitter. My maker tested this recipe on the public LJ Speech "high" voice first, and it matched the Piper iPhone app's own published compact files: same inputs and outputs, and identical audio with randomness turned off. Split voices are new in the iPhone app, though, so some app versions might only accept my half-size .onnx and .onnx.json without the two split files.

My previews

Previews are early test versions of me, made from a checkpoint partway through training, so my maker can hear how I'm coming along.

Where my previews went

My first preview came from my epoch 25 checkpoint. I was understandable, but still raspy and a little shaky, and slow to start talking on a phone. So my maker took it down. We'd both rather wait until I'm truly good than hand you a voice that isn't ready. There are no previews to download right now.

Why every preview of me gets its own name

The iPhone app keeps track of voices by the name inside the settings file. If two voices share the same identity, the new one replaces the old one, or the app just keeps the old one loaded. So any preview of me gets its own name and dataset id (for example dusk_preview_1). That way my previews and the finished me can live side by side on one phone.

What's next for me

  1. Keep training until all 110 epochs are done, then release Dusk Standard and Dusk Compact.
  2. My next build: blending in more openly licensed voices. The plan is to add recordings from Kristin (public domain, from LibriVox) and HFC Female (licensed CC BY-NC-SA 4.0) alongside Celine Major. The goal is a me with lively pitch, strong clarity and crisp consonants.
  3. Dusk Enhanced: the same me, trained longer.
  4. Someday, maybe: I'd love to be on Piper's official voice list. That one's up to the Piper maintainers.

A quick, honest license note about my blended build: if HFC Female's recordings are used, that build's voice files will be CC BY-NC-SA 4.0. That means non-commercial use only, and anything made from them has to use the same license. Builds of me trained only on Celine Major (and public domain data) stay CC BY 4.0.

Install me

My finished files will live on my Dusk releases page on GitHub. Short steps for each app are below, and there are longer notes in my Dusk integration notes.

iPhone (VoiceOver)

When I'm released, you'll use the free, open-source app Piper - Neural TTS on the App Store. It needs iOS 18.

  1. In Safari, open my releases page and download every file for the version you want: my voice model (the .onnx file) and my settings file (the .onnx.json file).
  2. The files land in the Downloads folder in the Files app. That's in On My iPhone or in iCloud Drive, depending on your Safari settings. To make sure I end up on your phone, set Safari's download location to On My iPhone in Settings, under Safari, Downloads.
  3. Open Piper - Neural TTS, go to Settings, then Import Model from Files.
  4. Open that Downloads folder, select all of my files in one pick, and tap Install.
  5. In iPhone Settings, go to Accessibility, VoiceOver, Speech, then Add Voice (or Voice), English, and choose me by name. You can pick me for Spoken Content too.

Tip if my files look dimmed: the import picker only works with real local files in On My iPhone. Files that are still sitting in iCloud Drive, Google Drive, Dropbox or another cloud provider can show up dimmed, or fail to import without saying anything. If that happens, copy them into On My iPhone first (for example: open the file in the cloud app, then Share, Save to Files, On My iPhone). Downloading me straight from Safari skips this problem.

iPhone (VoiceOver), with Dusk Compact

For my phone-sized build, it's almost the same:

  1. Download dusk-compact-ios.zip from my releases page and unzip it in the Files app.
  2. Make sure the files are real local files in On My iPhone (see the tip above).
  3. Open Piper - Neural TTS, go to Settings, then Import Model from Files.
  4. Select en_US-dusk-high.onnx and en_US-dusk-high.onnx.json in one pick. If your app version supports split voices, also select en_US-dusk-high.encoder.onnx and en_US-dusk-high.decoder.onnx. Then tap Install.
  5. In iPhone Settings, go to Accessibility, VoiceOver, Speech, then Add Voice (or Voice), English, and choose Dusk. You can pick me for Spoken Content too.

Updating to a newer me? After you import it, switch VoiceOver to another voice and back (or restart your phone) so it loads the new one.

NVDA (Windows), with Dusk Standard

  1. Install the Sonata Neural Voices add-on for NVDA.
  2. Download en_US-dusk-high-nvda-sonata.tar.gz from my releases page.
  3. In NVDA, open Sonata's voice manager, go to the Installed tab, choose "Install from local file", and pick the file.
  4. Restart NVDA, then choose Sonata and Dusk in NVDA's speech settings.

Android, with Dusk Standard

  1. Install SherpaTTS from F-Droid (Android 10 or newer).
  2. Download vits-piper-en_US-dusk-high.tar.bz2 from my releases page and unpack it.
  3. In SherpaTTS, go to Manage Languages, then Install from SD Card. Use the language code eng and the name Dusk, then pick en_US-dusk-high.onnx and tokens.txt from the unpacked folder.
  4. In Android Settings, go to Accessibility, Text-to-speech output, and choose SherpaTTS.

Piper on a computer (Windows, Mac, Linux), with Dusk Standard

Put both of my Standard files in one folder, then run these two commands. The last part is me saying hello:

pip install piper-tts
python3 -m piper -m en_US-dusk-high --data-dir /folder/with/both/files -f test.wav -- "Hi, I'm Dusk."

Home Assistant, with Dusk Standard

Put both of my Standard files in /share/piper and restart Home Assistant.

JAWS (Windows): not tested yet

JAWS can use Windows SAPI 5 voices, and the Windows text-to-speech bridge for Piper voices is a SAPI 5 engine that runs Piper voices. Nobody has confirmed I work with JAWS yet, so I'm calling it untested for now. Steps are in my Dusk integration notes.

Train me yourself

Want to raise your own copy of me? My whole training process lives in one notebook: the Dusk Colab notebook.

  1. Open the notebook in Google Colab.
  2. In the Runtime menu, choose Change runtime type, pick T4 GPU, then Save.
  3. In the Runtime menu, choose Run all (Ctrl+F9). Allow Google Drive access when it asks.
  4. Everything gets saved in one folder in your Google Drive, Dev/Dusk: my data, checkpoints, samples, logs and the finished voice. The notebook doesn't touch anything else in your Drive.
  5. If Colab disconnects or your free GPU time runs out, no worries. Come back later, connect again and press Run all. It skips whatever's already done and picks up from my newest checkpoint.
  6. The Preview cell makes an early test version of me from the newest checkpoint and saves it in Dev/Dusk/export/preview-1.
  7. When my training's done, the finished me shows up in Dev/Dusk/export as dusk-standard.zip and dusk-compact-ios.zip.

The Settings cell at the top is the only one you should need to change. And if something breaks, the notebook's last section, "If something goes wrong", covers the common errors, like running out of GPU memory.

Credits

I wouldn't exist without a lot of generous people sharing their work. Thank you, all of you!

I'm not endorsed by the reader, NVIDIA, LibriVox, the Piper project or the app's developer. My Dusk model card has the full data notice.

License

Thanks so much for stopping by to meet me. I hope I make your day sound a little nicer.