Phi 4 Multimodal Instruct
Microsoft · released Feb 24, 2025 · microsoft/Phi-4-multimodal-instruct
Speech to textTranscribes a recording into words
- Type
- Open weightsMIT License
- Languages
- 23
- Size
- 5.6B
Context measured in tokens
Our take
Written Aug 2, 2026Phi 4 Multimodal Instruct is a six-billion-parameter speech-to-text model from Microsoft with a permissive MIT licence. It turns audio into written text with excellent accuracy on clean recordings and very fast batch processing, though it struggles with meetings and accented speech.
Pick this for clean, prepared speech or high-throughput batch jobs. Use it for broad language coverage with no licensing restrictions. Skip it if you need meetings or accented transcription, or a hosted API rather than self-hosting.
The case for it
- Extremely fast batch transcription: 163 times real time, processing an hour of audio in about 22 seconds on benchmark hardware.
- Nearly flawless on clean read-aloud audio, with roughly one word wrong per 74 words.
- Permissive MIT licence allows commercial use, modification, and redistribution.
- Broad language support across 23 languages including Arabic, Chinese, Czech, Danish, Dutch, English, Finnish, and French.
The case against it
- Accuracy collapses in challenging audio conditions: podcasts and video are nearly six times worse than clean speech, and meetings are worse still.
- No hosted inference options available; you must self-host.
- Active parameter count is undisclosed, so the efficiency claim is unverified in our data.
How good is it?
TranscriptionTurning speech into text3.5 of 5Open ASR WER · 29th of 74
94.6%
Misses roughly one word in 18, averaged over nine English test sets.
163×50th of 62
an hour of audio in 22 seconds, on the board's own hardware. Your machine will differ.
23
Listed on the model card. The accuracy above is English only.
Percentage of words wrong on each set, lower better. Bars are scaled to this model's own worst case, not to the board.
Which languages ↓ ↑
Arabic · Chinese · Czech · Danish · Dutch · English · Finnish · French · German · Hebrew · Hungarian · Italian · Japanese · Korean · Norwegian · Polish · Portuguese · Russian · Spanish · Swedish · Thai · Turkish · Ukrainian
The figures above come from the Open ASR Leaderboard, an independent public test that runs every model on the same recordings. It is the only measurement of transcription quality we know of, so there are no other scores to show.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done, which is why they get no rating.
Every published score for this model9 scoresEvery figure we hold, from 9 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Can you run it yourself?
- Fits in memory
- weights load entirely on the card
- Spills to system RAM
- some weights offload; much slower
- Too large
- will not load even with offload
- est
- size is calculated; the verdict could change by 10%
Comfortable fit
GeForce RTX 4090 · 24 GB
Room to spare. 17.7 GB spare means a 10% error in the size would not change the answer.
GeForce RTX 5090 · 32 GB
Room to spare. 25.7 GB spare means a 10% error in the size would not change the answer.
Apple M2 (8-core GPU, 8GB unified) · 8 GB
Room to spare. 0.9 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.
Check against your own machine → · All 71 devices, with every size →
When we formed this view
Dates behind this page
Prices last checked 6h ago
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
Licence and identifiers
What the licence allowsMIT License, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
MIT License
Fully permissive: do anything with attribution. No patent grant, unlike Apache-2.0.
Identifiers
- Hugging Face
- microsoft/Phi-4-multimodal-instruct
- Architecture
- Dense
- Modality record
- audio->text
- Catalogue slug
- microsoft-phi-4-multimodal-instruct