Moonshine Medium Streaming (English)
Moonshine Medium Streaming (English) is a 245M-parameter speech-to-text model from Moonshine AI, released under the MIT license. The reviewed source lists English, and the model is designed for native streaming. Among the common setups we test, it ranks highest for live captions and voice input (#3 of 26 in the matcher).
English streaming ASR for latency-sensitive local applications. Current Moonshine documentation lists Medium Streaming at 245M parameters.
Key facts
| Provider | Moonshine AI |
|---|---|
| Model family | Moonshine |
| Parameters | 245M |
| License | MIT · Permissive — license text ↗ |
| Language coverage | English |
| Streaming | Native streaming architecture |
| Timestamps | Limited or runtime-dependent |
| Speaker diarization | No — needs a separate component |
| Speech translation | No |
| Documented runtimes | moonshine-voice (Python), ONNX Runtime core, Swift, Android and C++ libraries — how to run it |
| Primary source | github.com/Agenteryx/Moonshine ↗ |
| Last reviewed |
Hardware and workload fit
These are Speech Model Match's conservative 1–5 editorial ratings, relative to the other 19 reviewed models. They come from model size, official memory guidance and documented runtimes — not from a universal benchmark. How the ratings work.
| Dimension | Rating | Scale |
|---|---|---|
| CPU-only fit | 4/5 | |
| Apple Silicon fit | 5/5 | |
| NVIDIA GPU fit | 4/5 | |
| Speed | 5/5 | |
| Accuracy (relative) | 4/5 | |
| Low memory use | 4/5 | |
| Long recordings | 3/5 | |
| Live / low latency | 5/5 | |
| Subtitle work | 3/5 | |
| Edge / low-power devices | 4/5 |
Where it is strong
- Native streaming architecture for live, low-latency transcription
- CPU-only fit: rated 4/5
- Apple Silicon fit: rated 5/5
- NVIDIA GPU fit: rated 4/5
- Speed: rated 5/5
- Accuracy (relative): rated 4/5
- Low memory use: rated 4/5
What to check first
- No native speaker diarization — pair it with a separate diarization pipeline if you need speaker labels
- Timestamp support is limited or runtime-dependent — test it if you need subtitles
- English-only: not suitable for other languages
How it ranks in common setups
Ranks come from the same deterministic matcher that runs on the homepage, applied to all 26 reviewed models. They are decision guidance, not accuracy claims.
| Setup | Rank | Fit score | Top match |
|---|---|---|---|
| Long recordings on an 8–12 GB NVIDIA GPU, balanced | #20 of 26 | 67/100 · Possible fit | Whisper turbo |
| Live captions or voice input (native streaming + timestamps, speed first) | #3 of 26 | 86/100 · Excellent fit | Nemotron 3.5 ASR Streaming 0.6B |
| Subtitles with timing, accuracy first | #17 of 26 | 67/100 · Possible fit | Whisper medium |
| Meetings with speaker labels (diarization + timestamps) | #20 of 26 | 64/100 · Possible fit | VibeVoice-ASR 7B |
| CPU-only machine, low memory use | #8 of 26 | 67/100 · Possible fit | VibeVoice-ASR-BitNet |
| Apple Silicon with 8–16 GB unified memory, long recordings | #6 of 26 | 72/100 · Strong fit | Whisper small |
| Japanese live transcription (native streaming, speed first) | Not ranked (language not listed) | — | Nemotron 3.5 ASR Streaming 0.6B |
Supported languages
- English
en
Compare coverage across every reviewed model in the language support matrix.
How to run Moonshine Medium Streaming (English) locally
Moonshine ships a cross-platform library built on ONNX Runtime with Python, Swift, Android and C++ bindings. Runtimes below are the ones the official model card or repository documents for this model (checked November 2, 2026).
- moonshine-voice (Python) ↗Official package · includes a microphone demo
- ONNX Runtime core ↗Framework · 8-bit quantized .ort models
- Swift, Android and C++ libraries ↗Official package · iOS, macOS, Android, Windows, Linux, Raspberry Pi
Install command shown in the official github.com page ↗:
pip install moonshine-voice
Audio input: Any chunk length and sample rate is accepted as long as the audio is mono; it is converted to 16 kHz internally.
Official hardware guidance: 245M parameters, 8-bit weights. Published latency: 107 ms on a MacBook Pro, 269 ms on Linux x86, 802 ms on a Raspberry Pi 5. Source ↗
Whatever runtime you choose, measure speed and accuracy on your own audio with the benchmark tool; results differ a lot between runtimes, precision and hardware.
Before you deploy Moonshine Medium Streaming (English)
A printable checklist built from the facts on this page. Tick it off before putting the model into production.
- Language. Confirm your language is in the 1-language list on this page (this model is single-language), and test any accents or code-switching you expect.
- License. MIT: Include the copyright notice and the permission notice in all copies or substantial portions. Provided as is, without warranty. License guide.
- Install. Start from the official command:
pip install moonshine-voice(full run notes). - Audio input. Any chunk length and sample rate is accepted as long as the audio is mono; it is converted to 16 kHz internally.
- Hardware. 245M parameters, 8-bit weights. Published latency: 107 ms on a MacBook Pro, 269 ms on Linux x86, 802 ms on a Raspberry Pi 5.
- Features you rely on. For Moonshine Medium Streaming (English), native streaming is documented; timestamps are limited or runtime-dependent; speaker labels need a separate diarization component. Test each one you need with real audio.
- Measure. Run 10–20 representative clips, score them with the WER calculator and record speed in the benchmark workspace before you commit.
Alternatives and related models
Same family: Moonshine Tiny Streaming (English).
Similar fit profile: Granite Speech 5.0 470M TurboCTC (IBM, 470M), Whisper base (OpenAI, 74M), Omnilingual ASR CTC 300M (Meta AI, 325M). Similarity is computed from the ten fit ratings plus streaming and diarization support.
| Fact | Moonshine Medium Streaming (English) | Moonshine Tiny Streaming (English) |
|---|---|---|
| Provider · size | Moonshine AI · 245M | Moonshine AI · 34M |
| License | MIT Permissive | MIT Permissive |
| Languages | English | English |
| Streaming | Native | Native |
| Timestamps | Limited | Limited |
| Speaker diarization | Separate pipeline | Separate pipeline |
| CPU · Apple · NVIDIA fit | 4/5 · 5/5 · 4/5 | 5/5 · 5/5 · 4/5 |
| Live · long recordings | 5/5 · 3/5 | 5/5 · 3/5 |
| Main runtime | moonshine-voice (Python) | moonshine-voice (Python) |
Compare Moonshine Medium Streaming (English) side by side
Guides that cover Moonshine Medium Streaming (English)
- Moonshine vs Whisper: live voice or general-purpose ecosystem?
- Best local speech-to-text models in 2026
- Best local Whisper alternatives in 2026
- Best local speech-to-text models for CPU-only PCs
- Best local speech-to-text models for streaming
- Best local speech-to-text models for Apple Silicon
Check Moonshine Medium Streaming (English) for your setup
Pick your language, hardware and workload to see this model's fit score, the reasons behind it and where it ranks against all reviewed models. Everything runs in your browser.
Common questions
Can I use Moonshine Medium Streaming (English) commercially?
Permissive license; commercial use is allowed under the listed terms. The listed license is MIT; read the current license text ↗ before shipping a product, because terms can change. The license guide compares the obligations of all 26 reviewed models.
Does Moonshine Medium Streaming (English) support real-time streaming?
Yes. The reviewed source describes a native streaming architecture, so it is a candidate for live captions, dictation or voice agents. Measure end-to-end latency on your own hardware.
Which languages does Moonshine Medium Streaming (English) transcribe?
English only. For other languages pick a multilingual model; the language support matrix shows which reviewed models list each language.
Can Moonshine Medium Streaming (English) tell speakers apart?
Not natively. Combine it with a dedicated diarization component and evaluate that component separately; the meetings guide covers this workflow.
Primary sources
Reviewed against primary sources on September 16, 2026. Model behavior, runtime support, language coverage and licenses can change; re-check the linked primary source before production use. See the full source directory.