Update mlx-swift to 0.30.6 — fixes static audio on iPhone 16 Pro - #29
Open
whothisbeme wants to merge 1 commit into
Open
Update mlx-swift to 0.30.6 — fixes static audio on iPhone 16 Pro#29whothisbeme wants to merge 1 commit into
whothisbeme wants to merge 1 commit into
Conversation
mlx-swift 0.30.2 produces static/corrupted audio on iPhone 16 Pro due to two NAX (Neural Accelerator) bugs: 1. Incorrect NAX hardware detection on A18 chip (ml-explore/mlx#3083) - A18 (gen 17) was wrongly detected as having NAX support (gen 18+) - Caused silently wrong numerical output instead of a crash 2. NAX overflow in ConvTransposed1d (ml-explore/mlx#3092) - Incorrect output for large tensors (time dim > ~8000) - Directly affects Kokoro's vocoder transposed convolutions Both fixes are included in mlx-swift 0.30.6. Using `from:` instead of `exact:` allows downstream consumers to resolve compatible versions. Relates to: mlalma/KokoroTestApp#7, ml-explore/mlx-swift#344
dakshaymehta
added a commit
to dakshaymehta/kokoro-ios
that referenced
this pull request
Apr 10, 2026
mlx-swift 0.30.2 has two NAX bugs that cause static/corrupted audio: - Incorrect NAX hardware detection (ml-explore/mlx#3083) - NAX overflow in ConvTransposed1d (ml-explore/mlx#3092) Both fixed in mlx-swift 0.30.6. Also changes pin style from exact to from to allow downstream consumers to resolve compatible versions. Ref: mlalma#29
mikaelhatanpaa
added a commit
to mikaelhatanpaa/kokoro-ios
that referenced
this pull request
May 20, 2026
mlx#3083 (NAX hardware detection wrong on A18) and mlx#3092 / mlx-swift#344 (ConvTransposed1d produces partially-wrong output when T > ~8000 on iOS Metal) combine to produce alternating clean speech / sustained tinnitus-like buzz mid-content when Kokoro's vocoder runs on iPhone. PCM samples appear clean (peak ~0.5) but ~50% of frames in the bad region are garbage at T > 15840. Fixed in 0.30.6+; confirmed clean by mlalma/kokoro-ios PR mlalma#29.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
exact: "0.30.2"tofrom: "0.30.6"exacttofromto allow downstream consumers to resolve compatible versionsProblem
On iPhone 16 Pro (A18 chip), Kokoro TTS generates white noise / static instead of speech when using mlx-swift 0.30.0–0.30.3. Audio sample values range -11 to +11 instead of the expected -0.33 to +0.54.
Root Cause
Two bugs in mlx-swift's upstream mlx library:
Incorrect NAX hardware detection (ml-explore/mlx#3083) — The A18 chip (generation 17) was incorrectly detected as having Neural Accelerator (NAX) support, which is only available on generation 18+ (iPhone 17 Pro). When NAX was wrongly enabled, computations produced silently wrong numerical results.
NAX overflow in ConvTransposed1d (ml-explore/mlx#3092) — On iOS, transposed convolutions produced incorrect output for large tensors (time dimension > ~8000), directly affecting Kokoro's vocoder.
Both fixes are included in mlx-swift 0.30.6.
Testing
Verified with kokoro-ios 1.0.10 + mlx-swift 0.30.6 on iPhone 16 Pro — clear audio output with correct sample values.
Related Issues