Downloads · 30 days
7
32% of all-time downloads
ace-nowork/paul-graham-voice-model-phone
paul-graham-voice-model-phone is a text-to-speech model from ace-nowork. Use it when you need text read aloud. It is set up for piper. The card lists the license as mit.
A small, on-device English text-to-speech voice, built to narrate essays on a phone with no server and no GPU.
Downloads · 30 days
7
32% of all-time downloads
All-time downloads
22
Public
Repo size
64.3 MB
Likes
0
Public
Click a slice to open those files.
.onnx63.5 MB · 99%
From the Hugging Face model README
A small, on-device English text-to-speech voice, built to narrate essays on a phone with no server and no GPU.
en-us)This voice imitates the reading style of essayist Paul Graham. Two things are worth stating plainly:
Do not use this model to impersonate anyone, to attribute words to a person who did not say them, or to produce audio intended to be mistaken for a real recording. Label output as synthetic wherever it is published.
With sherpa-onnx (works on desktop, Android and iOS):
import sherpa_onnx
tts = sherpa_onnx.OfflineTts(
sherpa_onnx.OfflineTtsConfig(
model=sherpa_onnx.OfflineTtsModelConfig(
vits=sherpa_onnx.OfflineTtsVitsModelConfig(
model="phonepg.onnx",
tokens="tokens.txt",
data_dir="espeak-ng-data", # ships with sherpa-onnx
),
num_threads=2,
provider="cpu",
)
)
)
audio = tts.generate("Text to read aloud.", sid=0, speed=1.0)
The ONNX file carries the metadata sherpa-onnx expects (sample_rate, voice,
has_espeak, …). tokens.txt contains only single-codepoint phonemes, since
that is what sherpa-onnx's Piper lexicon accepts — the multi-codepoint diphthong
entries in the original Piper config are never emitted by espeak and are omitted.
For the standard Piper runtime, use phonepg.onnx with phonepg.onnx.json.
| file | what it is |
|---|---|
phonepg.onnx | the model, with runtime metadata embedded |
phonepg.onnx.json | Piper config: phoneme map and inference defaults |
tokens.txt | phoneme → id table for sherpa-onnx |
sample-billionaires-build-60k.wav | ~17 s of output from this checkpoint |
The sample reads the opening few sentences of Paul Graham's essay "Billionaires Build" — a short excerpt used to demonstrate the voice. The text is his and remains his; read it at the link.
Narrated essays are being published here:
They go up one at a time, every day — each one is watched end to end before it is published, so the whole catalogue is not there yet and the list keeps growing. If the essay you want is missing, it is probably still in the queue.
(Those videos are narrated with a larger model; this repo is the small one that runs on a phone. Both are synthetic — see the note above.)
MIT, following the Piper base checkpoint it was fine-tuned from. The licence covers the model weights; it is not permission to impersonate anyone.