YuE2-3B in Russian: an open model that sings Cyrillic
Open song-generation models usually stumble on Russian: you have to rewrite the lyrics in Latin script, and the vocals still carry a foreign accent. We rented a GPU, installed YuE2-3B and fed it Russian lyrics in ordinary Cyrillic — no transliteration, no language hints. Below are three tracks, the measurements and a blind intelligibility check.
Tested on 16 September 2026 on a rented NVIDIA A40. Rental cost about 40 cents. The lyrics were written by us specifically for this test.
In short
Cyrillic works. Lyrics in ordinary Cyrillic, no transliteration. Pronunciation is clean, stress is correct, no foreign accent.
Intelligibility verified by machine. Blind speech recognition identified the language as Russian with 100% confidence and returned the lyrics near-verbatim.
Stereo, and fast. Output is genuine 48 kHz stereo, not duplicated mono. It runs faster than real time and needs about 9 GB of VRAM.
The licence is non-commercial, though. Free for personal use, including earning from your own tracks. A company has to negotiate with the authors separately.
Listen for yourself
“Ne gasni” — dark alt-rock, male baritone
2:47 of audio generated in 119 seconds. Loudness −13.6 LUFS.
“Steklo” — synth-pop, female vocal
2:37 of audio in 118 seconds. Loudness −11.9 LUFS.
“Vzlyotka” — folk-rock ballad, male tenor
1:44 of audio in 89 seconds. Loudness −14.5 LUFS.
How we checked intelligibility
Judging by ear lets you forgive anything, so we handed the finished tracks to a speech recognizer blind — without showing it the source lyrics. It identified the language as Russian with 100% confidence and returned the words near-verbatim.
Written vs heard
“Kak posledniy tyoplyy bilet” (ticket) → heard as vzglyad (glance)
“Vzdokh sentyabrya” (a sigh of September) → heard as Sdokh (dropped dead)
third track — recognised in full, no discrepancies
These are mishearings, not mis-singings: similar-sounding words confused, rather than noise instead of speech.
The numbers
Metric
Track 1
Track 2
Track 3
Duration
2:47
2:37
1:44
Generation time
119 s
118 s
89 s
Faster than real time
1,4×
1,3×
1,2×
L/R correlation
0,86
0,91
0,61
Loudness
−13,6 LUFS
−11,9 LUFS
−14,5 LUFS
Truncation
no
no
no
Channel correlation below 1.0 means the stereo is genuine, not the same track in both ears. VRAM under load was about 9 GB; the weights take 7.3 GB plus a 0.5 GB audio decoder.
How it compares with HeartMuLa
We tested another open model the same day — HeartMuLa 3B. The comparison is useful because it shows what “the model knows Russian” actually means.
HeartMuLa 3B
YuE2-3B
Russian in Cyrillic
does not work
works
Transliteration needed
yes
no
Accent
foreign
clean
Channels
mono
48 kHz stereo
VRAM
~20 GB
~9 GB
Licence
Apache 2.0
CC BY-NC + permission
So it is a trade-off: HeartMuLa has the free licence but no Russian; YuE2 has the Russian but a stricter licence. Details on the former are in a separate write-up.
The licence: read it before you install
This is a case where the licence matters more than the measurements. YuE2 weights are released under CC BY-NC 4.0 — non-commercial — plus a separate permission from the authors.
For yourself — allowed. The authors explicitly allow personal use and state they take no fees or royalties on money you earn from the tracks you create.
For a company — by agreement. If the weights are used by an organisation rather than an individual, a separate licence is required. There is no public price list; terms are discussed by email.
This is not legal advice. We are summarising what MODEL_LICENSE said at the time of the test. Terms may change — check the original.
Verdict
For Russian this is the first open model that needs no humiliating workarounds: no rewriting lyrics in Latin script, no living with an accent. The audio is genuine stereo rather than an imitation, and it generates faster than it plays. The barrier to entry is low: nine gigabytes of VRAM is enough.
An honest caveat: three tracks are a check, not a benchmark. We did not measure how the model handles long forms, unusual time signatures or rare genres, and we did not blind-test it against commercial services. We checked exactly one question — does it sing Russian intelligibly. It does.
Style is easier to get from a prompt
Running your own model means a GPU, a setup and a licence. If you need a specific sound right now, a ready style prompt is faster: our catalog has them by artist and genre.
Does it really sing Russian without transliteration?
Yes. We wrote the lyrics in ordinary Cyrillic, with no Latin script and no language hint in the settings. Pronunciation is clean, word stress is correct, there is no foreign accent. That is the key difference from HeartMuLa, where Cyrillic produced gibberish and the text had to be rewritten in Latin letters.
How did you verify the words are intelligible?
Not by ear. We ran the finished tracks through Whisper large-v3 blind — without giving it the source lyrics. The language was detected as Russian with 100% confidence and the words came back near-verbatim. The differences were ordinary speech-recognition errors on sung vocals.
What GPU do I need?
Under load the model used about 9 GB of VRAM, so a 12–16 GB card is enough. We rented a 48 GB A40 at $0.49/hour, but that much memory was never needed.
Is it fast?
Faster than real time by 1.2–1.4×: a 2:47 track was generated in 119 seconds. All three of our runs finished within a minute or two.
Can it be used commercially?
Not by default. The weights are released under CC BY-NC 4.0 — non-commercial — plus a separate permission from the authors. Personal use is free, and the authors state they take no fees or royalties on what you earn from your own tracks. Use of the weights by a company, however, must be agreed separately: there is no public price list.
Will it replace Suno?
For Russian this is the first open model where the question is even worth asking. But we will not rank it on quality: three tracks are a check, not a benchmark. And keep the licence in mind — with Suno you pay a subscription, here you negotiate with the authors if it is for business.