Ollama · phonon

Phonon is [Gradium's](https://huggingface.co/gradium) text-to-speech family. It turns written text into spoken audio as it generates, making it useful for reading assistant replies, narrating passage…

ollama/phonon

Phonon is [Gradium's](https://huggingface.co/gradium) text-to-speech family. It turns written text into spoken audio as it generates, making it useful for reading assistant replies, narrating passages, and adding a voice to local apps.

```shell ollama run phonon "Good morning. Here is a short update before your first meeting." ```

The default model is [Phonon 31M English](https://huggingface.co/gradium/phonon-31m-en). It includes one voice, named `default`. Choose a 40M model for another language or for the multilingual checkpoint:

| Ollama tag | Language | Loaded memory on Apple M5 Max | |---|---|---:| | `phonon` (`phonon:31m-en`, `phonon:en`) | English, 31M | 121 MB | | `phonon:40m-en` | English, 40M | 141 MB | | `phonon:40m-fr` (`phonon:fr`) | French, 40M | 141 MB | | `phonon:40m-de` (`phonon:de`) | German, 40M | 141 MB | | `phonon:40m-es` (`phonon:es`) | Spanish, 40M | 141 MB | | `phonon:40m-pt` (`phonon:pt`) | Portuguese, 40M | 141 MB | | `phonon:40m-multilingual` (`phonon:multilingual`) | All five languages, 40M | 141 MB |

The 31M English checkpoint is released under [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0). The [40M English](https://huggingface.co/gradium/phonon-40m-en), [French](https://huggingface.co/gradium/phonon-40m-fr), [German](https://huggingface.co/gradium/phonon-40m-de), [Spanish](https://huggingface.co/gradium/phonon-40m-es), [Portuguese](https://huggingface.co/gradium/phonon-40m-pt), and [multilingual](https://huggingface.co/gradium/phonon-40m-multilingual) checkpoints are released under [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/), which limits use to noncommercial purposes.

Phonon produces 24 kHz mono audio. These Ollama packages require Apple Silicon and Ollama 0.40.9 or later. Give the model text intended to be spoken; formatting marks such as Markdown headings may be read aloud. For saving audio or using the speech API, see the [Ollama speech guide](https://docs.ollama.com/capabilities/speech).

Specifications & capabilities

Published model ID
phonon

Deployments & artifacts

1–14 / 14

ollama

source id
ollama
execution mode
local
parameter count is approximate
false
context window
8000
context window is approximate
true
artifact size bytes
103678868
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter count is approximate
false
context window
8000
context window is approximate
true
artifact size bytes
125613179
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter count is approximate
false
context window
8000
context window is approximate
true
artifact size bytes
131759299
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter count is approximate
false
context window
8000
context window is approximate
true
artifact size bytes
128686969
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter count is approximate
false
context window
8000
context window is approximate
true
artifact size bytes
126125017
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter count is approximate
false
context window
8000
context window is approximate
true
artifact size bytes
148404925
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter count is approximate
false
context window
8000
context window is approximate
true
artifact size bytes
125358014
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter count is approximate
false
context window
8000
context window is approximate
true
artifact size bytes
122569416
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter count is approximate
false
context window
8000
context window is approximate
true
artifact size bytes
103678868
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter count is approximate
false
context window
8000
context window is approximate
true
artifact size bytes
122570736
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter count is approximate
false
context window
8000
context window is approximate
true
artifact size bytes
122570429
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter count is approximate
false
context window
8000
context window is approximate
true
artifact size bytes
112861569
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter count is approximate
false
context window
8000
context window is approximate
true
artifact size bytes
122570489
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter count is approximate
false
context window
8000
context window is approximate
true
artifact size bytes
122573126
updated at
2026-11-16T08:10:06.079865+00:00

Original sources

1–2 / 2

Ollama · Model page ↗

Ollama · Catalog ↗

Source links

1–1 / 1

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace