A small, natural English text-to-speech model that runs offline on any CPU. 44 MB, no GPU, no cloud.
Junco is an 11.4M-parameter text-to-speech model from Flock Speech. It turns English text into natural 24 kHz speech on an ordinary CPU, faster than real time. It has no GPU, network or PyTorch dependency, and the full model is a 44 MB download.
Junco is the clear, neutral reading voice of the Flock Speech family: a good fit for voice assistants, screen
readers, notifications, narration and other on-device or edge AI speech output. Install it with
pip install flockspeech.
| Flock Speech voices | Style | Model card |
|---|---|---|
| Junco | clear, neutral reading voice | this page |
| Goldfinch | conversational voice that laughs and breathes on cue with [laugh] tags |
flockspeech/goldfinch |
| Developed by | Flock Speech |
| Model type | Neural text-to-speech: compact acoustic model + Vocos vocoder |
| Language | English (US) |
| Voices | 1 (female, read-aloud style) |
| Output | 24 kHz mono audio |
| Parameters | 11.4M acoustic model + 13.5M vocoder |
| Download | 44 MB (ONNX; int8 decoder, fp16 encoder and vocoder) |
| Runtime | ONNX Runtime on CPU (Linux, macOS, Windows; x86-64 and ARM64) |
| License | Apache-2.0 (vocoder weights MIT) |
| Version | v0.1, November 2026 |
All samples were made with the files in this repository at default settings (8 steps, seed 0), with no editing.
| Use | Text | Audio |
|---|---|---|
| Greeting | Hello! I'm Junco, a tiny voice that runs entirely on your own device. | |
| Assistant | Your next meeting starts in fifteen minutes. Would you like me to read the agenda? | |
| Narration | The old lighthouse keeper climbed the spiral stairs one last time, and watched the ships come home through the fog. | |
| News | Researchers announced on Tuesday that the new battery can be charged in under ten minutes, and lasts twice as long. |
The flockspeech Python package bundles these weights, so nothing is downloaded
at run time.
pip install flockspeech
flockspeech "Hello! I'm Junco." -o hello.wav --play
from flockspeech import Junco
tts = Junco() # loads in under a second
audio = tts("Hello there.") # float32 numpy array, 24 kHz mono
tts.save("Hello there.", "hello.wav")
# Low latency: audio is produced sentence by sentence
for chunk in tts.stream(long_text):
play(chunk)
To use the files in this repository directly:
from huggingface_hub import snapshot_download
from flockspeech import Junco
path = snapshot_download("flockspeech/junco", allow_patterns=["onnx/*"])
tts = Junco(model_dir=f"{path}/onnx")
| Parameter | Default | Effect |
|---|---|---|
speed |
1.0 | Speaking rate; 1.2 is 20% faster |
steps |
8 | Generation steps; 4 is about 1.5× faster with slightly lower quality |
seed |
0 | Fixes the small random variation in delivery, so output is reproducible |
threads |
up to 4 | CPU threads for ONNX Runtime |
Suitable for:
Out of scope:
Synthetic speech can be misused for deception. Junco produces a single fixed voice and cannot clone speakers, which limits impersonation risk. We still ask that you:
Text is converted to phonemes with espeak-ng, a compact neural acoustic model turns the phonemes into a mel spectrogram, and the Vocos vocoder (MIT) turns that into 24 kHz audio. All three run in ONNX Runtime on the CPU.
| File | Contents | Size |
|---|---|---|
onnx/encoder.onnx |
Acoustic model, part 1 (fp16 weights) | 7.2 MB |
onnx/decoder-int8.onnx |
Acoustic model, part 2 (int8) | 9.9 MB |
onnx/vocoder.onnx |
Vocos vocoder (fp16 weights) | 27.1 MB |
onnx/junco.json |
Mel normalisation statistics and default inference settings | <1 kB |
samples/ |
The audio samples above |
| Data | LJ Speech: 13,100 clips, about 24 hours, one speaker, public domain |
| Compute | 3 hours on one NVIDIA T4 GPU, from scratch |
Environmental impact. The final training run used about 3 GPU-hours on one NVIDIA T4 (70 W TDP), or about 0.2 kWh. Architecture experiments before it used more.
Does Junco need a GPU or an internet connection? No. It runs on an ordinary CPU with ONNX Runtime. Once installed, speech is generated fully offline and your text never leaves the machine.
How big is it? 44.2 MB in total: a 17.1 MB acoustic model plus the 27.1 MB Vocos vocoder. Junco and Goldfinch share the vocoder, so both voices together take 61.3 MB.
Can it run on a Raspberry Pi or other ARM boards?
It runs on 64-bit ARM Linux wherever onnxruntime and espeakng-loader publish wheels, including 64-bit Raspberry
Pi OS.
Can I stream audio for low latency?
Yes. tts.stream(text) yields audio sentence by sentence, so playback can start before the whole text is done.
Can I use it without Python?
The ONNX files run in any ONNX Runtime binding. The text front end (espeak-ng phonemes) and the small loop around the
three models live in the flockspeech package, which you can port.
Does it support voice cloning or other languages? No. Junco is one English (US) voice. For a casual, conversational voice, use Goldfinch.
Can I use it commercially? Yes. The weights are Apache-2.0 and the vocoder is MIT. The phonemiser (espeak-ng, phonemizer) is GPL-3.0 and is installed separately; see the License section below.
onnx/vocoder.onnx): MIT, © 2023 Charactr Inc. See onnx/LICENSE-vocos.Run-time dependency. Text-to-phoneme conversion uses espeak-ng and phonemizer. Both are GPL-3.0 and are not
included in this repository. The flockspeech package installs them as separate dependencies. If you plan to ship
Junco inside a closed-source product, review their licence terms, or replace the phonemiser with one under a licence
that suits you. See NOTICE.
@misc{flockspeech2026junco,
title = {Junco: a small text-to-speech model for on-device use},
author = {{Flock Speech}},
year = {2026},
howpublished = {\url{https://huggingface.co/flockspeech/junco}},
note = {Version 0.1}
}
We thank the authors of LJ Speech and of the Vocos vocoder.
onnx/vocoder.onnx 27 MBonnx/decoder-int8.onnx 10 MBonnx/encoder.onnx 7 MB