The short answer
Pick Moonshine when the model has to be as small as possible or run on iOS, in a browser or on a Raspberry Pi: its streaming models go down to 34 million parameters. Pick Phonon-2.5 for European languages (25 against Moonshine's 10 speech-to-text languages, most of them outside Europe) and for English accuracy: by Moonshine's own published numbers, Phonon-2.5 English has lower word error than Moonshine Medium Streaming on six of seven shared English sets.
Moonshine has no row in the Open ASR Leaderboard snapshot we compare against, and we have not run it, so the English comparison below uses Moonshine's own figures beside ours.
Side by side
Moonshine facts from github.com/moonshine-ai/moonshine, the moonshine-ai model cards on Hugging Face and moonshine-voice.readthedocs.io, read 2026-11-13.
| Phonon-2.5 | Moonshine (streaming models) | |
|---|---|---|
| Model type | Open weights on Hugging Face | Open weights |
| Size | 156 MB download (Phonon-2.5 English: 158 MB) | Tiny 34 M, Small 123 M, Medium 245 M parameters |
| Languages | 25 European languages (Phonon-2.5 English: English only) | English, Spanish, German, Mandarin, Japanese, Korean, Vietnamese, Tagalog, Ukrainian, Arabic |
| English word error, seven Open ASR sets | 5.06 % (Phonon-2.5 English: 4.82 %) | No row in the snapshot; Moonshine's own per-set figures below |
| Price | No per-hour fee when self-hosted | Free to run; no hosted price listed |
| Where it runs | Your hardware: CPUs (Linux x86-64 and arm64, Windows x86-64), Apple silicon, NVIDIA GPUs, Android | Python, JavaScript/WASM, iOS, Android, macOS, Linux, Windows, Raspberry Pi |
| Streaming | Yes, live WebSocket from fermion serve | Yes, designed for live audio |
| Diarization | No | Not mentioned in Moonshine's README |
| Word timestamps | Yes (--json output) | Not mentioned in Moonshine's README |
English: our numbers beside Moonshine's
Moonshine publishes per-set English word error for Moonshine Medium Streaming on the Open ASR Leaderboard's test sets, measured by Moonshine on its floating-point reference. Its 6.65 % headline average covers eight sets including TED-LIUM, so we show the seven sets both report rather than an average. On those seven, Phonon-2.5 English is lower on six; Moonshine Medium is lower on SPGISpeech (2.58 % against 3.31 %). The two columns come from different runs, so read the gaps as indicative.
| Test set | Phonon-2.5 | Phonon-2.5 English | Moonshine Medium Streaming (Moonshine's figures) |
|---|---|---|---|
| LibriSpeech clean | 1.60 | 1.64 | 2.08 |
| LibriSpeech other | 3.41 | 3.56 | 5.00 |
| AMI | 9.12 | 8.76 | 10.68 |
| Earnings-22 | 6.72 | 6.22 | 11.90 |
| GigaSpeech | 8.04 | 7.99 | 9.46 |
| SPGISpeech | 3.31 | 3.31 | 2.58 |
| VoxPopuli | 3.23 | 2.28 | 8.54 |
| Average of the seven | 5.06 | 4.82 | not published |
Where Moonshine is the better choice
- Smallest footprint: Tiny Streaming at 34 million parameters, and Moonshine's README lists models down to about 1 MB.
- Platforms Phonon does not ship for: iOS, the browser through WASM, and Raspberry Pi.
- Mandarin, Japanese, Korean, Vietnamese, Tagalog and Arabic.
- Streaming designed in: work starts while the user is still talking.
Where Phonon-2.5 is the better choice
- 25 European languages in one model, including French, Italian, Portuguese, Dutch, Polish and the Nordic and Baltic languages that Moonshine does not list.
- English accuracy: lower word error than Moonshine Medium on six of seven sets by Moonshine's own figures, most of all on earnings calls and VoxPopuli.
- A server with an OpenAI-shaped file route and a WebSocket stream from one command, plus Docker images for CPU and CUDA.
pip install fermion-research
fermion transcribe phonon-2.5 interview.wav --json
fermion serve phonon-2.5 # POST /v1/audio/transcriptions, GET /v1/audio/streamQuestions
- Is Phonon-2.5 more accurate than Moonshine?
- On English, by Moonshine's own published per-set figures for Moonshine Medium Streaming, Phonon-2.5 English has lower word error on six of seven Open ASR Leaderboard sets; Moonshine is lower on SPGISpeech. Moonshine is not in the leaderboard snapshot we use, and we have not run it.
- Which is smaller, Phonon-2.5 or Moonshine?
- Moonshine. Its streaming models have 34 million (Tiny), 123 million (Small) and 245 million (Medium) parameters. Phonon-2.5 is a 156 MB download.
- Does Moonshine run on iPhone or in the browser?
- Yes, Moonshine's README lists iOS and JavaScript/WASM as well as Android, desktop and Raspberry Pi. Phonon runs on CPUs, Apple silicon Macs, NVIDIA GPUs and Android.
- Which languages does Moonshine transcribe?
- Moonshine's README lists English, Spanish, German, Mandarin, Japanese, Korean, Vietnamese, Tagalog, Ukrainian and Arabic. Phonon-2.5 covers 25 European languages.
- Do both support live transcription?
- Yes. Moonshine's streaming models process audio while the user is speaking; Phonon streams through the WebSocket route of fermion serve.
Related
Sources and method
- Moonshine languages and platforms: github.com/moonshine-ai/moonshine, read 2026-11-13.
- Moonshine model sizes and English figures: huggingface.co/moonshine-ai/moonshine-streaming-medium and moonshine-voice.readthedocs.io/en/latest/models/available-models/, read 2026-11-13 (Moonshine's own measurements).
- Phonon-2.5 and Phonon-2.5 English: Fermion Research measurement, Phonon-2.5 release post (2026-10-22), Open ASR Leaderboard scoring code, full test sets of the same seven sets.
Canonical: https://www.fermionresearch.com/models/phonon-2-5/vs-moonshine/