Phonon 31m
An on-device voice small enough to ship inside an app, with its own Rust runtime.
gradium/phonon-31m-en on Hugging Face“Speaking is three to four times faster than typing for most people. With local dictation, you hold a key, say what you mean, and a small model on your own machine turns it into text. Nothing leaves your computer, there is no subscription, and it keeps working on a plane. The cleanup step removes filler words, fixes punctuation, and formats lists, so what lands in your editor reads like you typed it carefully.”
Memory
The most it held at once, from loading to the last test. Next to every other text to speech model here.
Speed
How long it takes to make speech, from the text going in to the last sample coming out.
Clarity
Twenty sentences full of numbers, times, addresses and codes. Whisper large-v3 turbo listened to each, and both sides were normalized, so “5” and “five” count as the same.
- 01
The quick brown fox jumps over the lazy dog.
“The quick brown fox jumps over the lazy dog.”· heard word for word
0:03 - 02
Please call me back at 415-555-0132 before five o'clock.
“Please call me back at 415-555-0132 before five o'clock.”· heard word for word
0:07 - 03
Send the invoice to billing@localflow.dev by Friday.
“Send the invoice to billing at localflow.dev by Friday.”· 1 word off
0:04 - 04
Our office is at 1600 Amphitheatre Parkway, Mountain View, CA 94043.
“Our office is at 1600 Amphitheatre Parkway, Mountain View, CA 94043.”· heard word for word
0:07 - 05
The meeting moved from 3:30 PM to 4:15 PM on March 3rd.
“The meeting moved from 3:30pm to 4:15pm on March 3rd.”· heard word for word
0:05 - 06
It costs $42.99, or about 39 euros with tax.
“It costs $42.99 or about €39 with tax.”· heard word for word
0:06
How it ran
Ran with ptts (Rust) on Vulkan, full precision, default voice on an AMD Radeon RX 9070 XT (16 GB, Vulkan through RADV (Mesa 26.2.2)). Measured with Phonon's own Rust bench tool (ptts) on Vulkan; ten runs after two warm-ups.