Skip to content

Pull requests: Blaizzy/mlx-audio

New pull request New
25 Open 401 Closed
25 Open 401 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Fix Voxtral STT crash on eos_token_ids initialization
#677 opened Apr 25, 2026 by contrapuntal Loading…
Add MOSS-TTS-Nano
#676 opened Apr 24, 2026 by lucasnewman Collaborator Loading…
3
Add batching support for Fish Speech S2 Pro
#675 opened Apr 24, 2026 by lucasnewman Collaborator Loading…
14
Add continuous batching support for Qwen3 TTS to the server
#674 opened Apr 23, 2026 by lucasnewman Collaborator Loading…
feat(higgs_audio): overlap-add mid-generation streaming
#669 opened Apr 23, 2026 by Kairos-a Contributor Loading…
4 tasks done
3
feat: add Mel-Band-RoFormer architecture for vocal source separation
#654 opened Apr 16, 2026 by xocialize Loading…
10 of 12 tasks
11
docs(qwen3-tts): add real-time streaming tuning guide
#646 opened Apr 11, 2026 by akaiHuang • Draft
1
feat(tts): Add batched ICL generation to improve speed for Qwen3-TTS
#644 opened Apr 10, 2026 by HFrost0 • Draft
3 tasks
feat (stt): Webserver: Diarization, export, Voxtral 3B Mini, larger audio files and enhanced model/language select
#643 opened Apr 10, 2026 by Gotanius Loading…
2
feat: Add VoxCPM2 TTS model (2B params, 48kHz, 30 languages)
#641 opened Apr 8, 2026 by acul3 Loading…
8 tasks done
20
feat: Add Vibevoice7B model support
#640 opened Apr 7, 2026 by Talpik Loading…
1
docs: add contributing guide, model porting guide, and code of conduct
#632 opened Apr 4, 2026 by beshkenadze Contributor • Draft
5
"feat(ui): add voice selector for Kokoro TTS
#602 opened Mar 24, 2026 by mh03r932 Loading…
3 tasks
2
perf(fish_speech): lazy RAS sampling - only resample on repetition
#600 opened Mar 24, 2026 by strongbinarycoder Loading…
4 tasks done
7
add MOSS-TTS
#586 opened Mar 17, 2026 by Li-dongyang Loading…
3 tasks done
32
Enable ref_audio and ref_text params in batch_generate and _prepare_batch_inputs for Qwen3-TTS model
#560 opened Mar 10, 2026 by chartjin15 Loading…
3 tasks
15
Fix LFM2.5-Audio sts audio
#516 opened Feb 19, 2026 by Blaizzy Owner • Draft
1
feat: add mlx support for IndexTTS2
#512 opened Feb 19, 2026 by 0xrushi • Draft
1 of 3 tasks
Add ACE-1.5
#499 opened Feb 15, 2026 by Blaizzy Owner • Draft
Optimize ACE-Step: NLC VAE, compiled decode, LoRA support
#498 opened Feb 15, 2026 by fspecii Loading…
6 of 9 tasks
2
Add InstructTTSEval module for TTS evaluation
#490 opened Feb 8, 2026 by Blaizzy Owner • Draft
Fix VibeVoice-ASR streaming via generate() and server mapping
#483 opened Feb 5, 2026 by JM27616 Loading…
1 of 3 tasks
1
3
[WIP] Create simple quickstart instructions and command
#476 opened Feb 2, 2026 by mnoukhov Contributor • Draft
1
feat: Full Chatterbox TTS Integration (Backend & UI)
#369 opened Jan 8, 2026 by jarodise Loading…
6
Improve Japanese TTS/STT UX and dependency handling
#260 opened Nov 8, 2025 by TechNavii Loading…
1 of 3 tasks
1
3
ProTip! Follow long discussions with comments:>50.