localai 4.4.3

[BrewTestBot]

Created by brew bump

---

Created with brew bump-formula-pr.

Details

release notes

What's Changed
Other Changes

chore: :arrow_up: Update CrispStrobe/CrispASR to d745bda4386ae0f9d1d2f23fff8ec95d76428221 by @localai-bot in chore: ⬆️ Update CrispStrobe/CrispASR to d745bda4386ae0f9d1d2f23fff8ec95d76428221 mudler/LocalAI#10260
docs: :arrow_up: update docs version mudler/LocalAI by @localai-bot in docs: ⬆️ update docs version mudler/LocalAI mudler/LocalAI#10259
chore: :arrow_up: Update antirez/ds4 to d881f2a05e8ff6bec001315a36b794b4aa310173 by @localai-bot in chore: ⬆️ Update antirez/ds4 to d881f2a05e8ff6bec001315a36b794b4aa310173 mudler/LocalAI#10262
chore: :arrow_up: Update mudler/parakeet.cpp to 9db92be63179a27201d3b88d5d40c545b2ac48ae by @localai-bot in chore: ⬆️ Update mudler/parakeet.cpp to 9db92be63179a27201d3b88d5d40c545b2ac48ae mudler/LocalAI#10263
feat(react-ui): add Indonesian language support by @dedyf5 in feat(react-ui): add Indonesian language support mudler/LocalAI#10266
chore: :arrow_up: Update ggml-org/llama.cpp to 4c6595503fe45d5a39f88d194e270f64c7424677 by @localai-bot in chore: ⬆️ Update ggml-org/llama.cpp to 4c6595503fe45d5a39f88d194e270f64c7424677 mudler/LocalAI#10261
feat(backend): locate-anything-cpp (open-vocabulary object detection via ggml) by @localai-bot in feat(backend): locate-anything-cpp (open-vocabulary object detection via ggml) mudler/LocalAI#10264
fix(router): production-ready request router + auto-size batch for embedding/rerank by @richiejp in fix(router): production-ready request router + auto-size batch for embedding/rerank mudler/LocalAI#10104
chore(model gallery): :robot: add 1 new models via gallery agent by @localai-bot in chore(model gallery): 🤖 add 1 new models via gallery agent mudler/LocalAI#10270
feat(parakeet-cpp): enable GGML_CUDA_GRAPHS in the cublas build by @localai-bot in feat(parakeet-cpp): enable GGML_CUDA_GRAPHS in the cublas build mudler/LocalAI#10273
fix(darwin): publish sherpa-onnx and speaker-recognition images for darwin/arm64 by @localai-bot in fix(darwin): publish sherpa-onnx and speaker-recognition images for darwin/arm64 mudler/LocalAI#10275
fix(crispasr): write piper TTS WAV at the model's native sample rate by @localai-bot in fix(crispasr): write piper TTS WAV at the model's native sample rate mudler/LocalAI#10277
feat(crispasr): bundle espeak-ng and add piper TTS voices to the gallery by @localai-bot in feat(crispasr): bundle espeak-ng and add piper TTS voices to the gallery mudler/LocalAI#10283
chore: :arrow_up: Update mudler/parakeet.cpp to b8012f11e5269126eddb7f4fd02f891a2ccc29b0 by @localai-bot in chore: ⬆️ Update mudler/parakeet.cpp to b8012f11e5269126eddb7f4fd02f891a2ccc29b0 mudler/LocalAI#10281
docs: :arrow_up: update docs version mudler/LocalAI by @localai-bot in docs: ⬆️ update docs version mudler/LocalAI mudler/LocalAI#10279
fix(mlx): route vision-language models to the mlx-vlm backend by @localai-bot in fix(mlx): route vision-language models to the mlx-vlm backend mudler/LocalAI#10274
fix(darwin): fix vibevoice-cpp build linkage + fail-safe go backend packaging by @localai-bot in fix(darwin): fix vibevoice-cpp build linkage + fail-safe go backend packaging mudler/LocalAI#10276
fix(agents): emit chat event timestamps in milliseconds (#9867) by @aniruddh909 in fix(agents): emit chat event timestamps in milliseconds (#9867) mudler/LocalAI#10243
fix(realtime): keep transcription model on a language-only session.update by @localai-bot in fix(realtime): keep transcription model on a language-only session.update mudler/LocalAI#10295
chore: :arrow_up: Update mudler/locate-anything.cpp to 92c1682da792c1e8a5dec91acc2be4b02c742ded by @localai-bot in chore: ⬆️ Update mudler/locate-anything.cpp to 92c1682da792c1e8a5dec91acc2be4b02c742ded mudler/LocalAI#10282
fix(config): backend-gate the top_k=40 sampler default (#6632) by @localai-bot in fix(config): backend-gate the top_k=40 sampler default (#6632) mudler/LocalAI#10285
feat(gallery): add 60 piper TTS voices across 42 languages (Phase 2) by @localai-bot in feat(gallery): add 60 piper TTS voices across 42 languages (Phase 2) mudler/LocalAI#10296
fix(deps): bump cogito to fix MCP image-result panic (#10101) by @localai-bot in fix(deps): bump cogito to fix MCP image-result panic (#10101) mudler/LocalAI#10294
fix(neutts): pin torchaudio to match torch (fixes undefined symbol) (#9798) by @localai-bot in fix(neutts): pin torchaudio to match torch (fixes undefined symbol) (#9798) mudler/LocalAI#10292
fix(gallery): make opus a meta backend for platform auto-selection (#9813) by @localai-bot in fix(gallery): make opus a meta backend for platform auto-selection (#9813) mudler/LocalAI#10291
chore(model gallery): :robot: add 1 new models via gallery agent by @localai-bot in chore(model gallery): 🤖 add 1 new models via gallery agent mudler/LocalAI#10298
fix(gallery): correct meta-backend definitions for platform auto-selection by @localai-bot in fix(gallery): correct meta-backend definitions for platform auto-selection mudler/LocalAI#10299
chore(model gallery): :robot: add 1 new models via gallery agent by @localai-bot in chore(model gallery): 🤖 add 1 new models via gallery agent mudler/LocalAI#10302
ci(darwin): build the ds4 backend for darwin/arm64 (metal) by @localai-bot in ci(darwin): build the ds4 backend for darwin/arm64 (metal) mudler/LocalAI#10303
fix(react-ui): stop Talk pipeline overflow and center collapsed-rail avatar by @localai-bot in fix(react-ui): stop Talk pipeline overflow and center collapsed-rail avatar mudler/LocalAI#10305
chore(model gallery): :robot: add 1 new models via gallery agent by @localai-bot in chore(model gallery): 🤖 add 1 new models via gallery agent mudler/LocalAI#10304
fix(react-ui): make agent chat timestamps format-agnostic (#9867) by @localai-bot in fix(react-ui): make agent chat timestamps format-agnostic (#9867) mudler/LocalAI#10290
model: fix case-insensitive suffix matching and skip .bak files in ListFilesInModelPath by @pos-ei-don in model: fix case-insensitive suffix matching and skip .bak files in ListFilesInModelPath mudler/LocalAI#10306
fix(xsysinfo): container-aware total RAM detection (cgroup/lxcfs) (#8059) by @localai-bot in fix(xsysinfo): container-aware total RAM detection (cgroup/lxcfs) (#8059) mudler/LocalAI#10288
feat(distributed): declarative per-model scheduling via env/args by @localai-bot in feat(distributed): declarative per-model scheduling via env/args mudler/LocalAI#10308
feat(sherpa-onnx): add Kokoro TTS + multilingual Piper voices by @localai-bot in feat(sherpa-onnx): add Kokoro TTS + multilingual Piper voices mudler/LocalAI#10309
feat(omnivoice-cpp): add OmniVoice TTS backend (file + streaming, voice cloning + voice design) by @localai-bot in feat(omnivoice-cpp): add OmniVoice TTS backend (file + streaming, voice cloning + voice design) mudler/LocalAI#10310
feat(i18n): add Korean (ko) translation by @moduvoice in feat(i18n): add Korean (ko) translation mudler/LocalAI#10312
feat(qwen3-tts-cpp): migrate to ServeurpersoCom/qwentts.cpp (streaming, speakers, voice design) by @localai-bot in feat(qwen3-tts-cpp): migrate to ServeurpersoCom/qwentts.cpp (streaming, speakers, voice design) mudler/LocalAI#10316
feat(realtime): gate realtime pipeline voice models behind voice recognition by @localai-bot in feat(realtime): gate realtime pipeline voice models behind voice recognition mudler/LocalAI#10319
chore: :arrow_up: Update vllm-project/vllm cu130 wheel to 0.23.0 by @localai-bot in chore: ⬆️ Update vllm-project/vllm cu130 wheel to 0.23.0 mudler/LocalAI#10314
test(e2e): live-server voice-recognition gate test by @localai-bot in test(e2e): live-server voice-recognition gate test mudler/LocalAI#10324

New Contributors

@aniruddh909 made their first contribution in fix(agents): emit chat event timestamps in milliseconds (#9867) mudler/LocalAI#10243
@moduvoice made their first contribution in feat(i18n): add Korean (ko) translation mudler/LocalAI#10312

Full Changelog: mudler/LocalAI@v4.4.2...v4.4.3

View the full release notes at https://github.com/mudler/LocalAI/releases/tag/v4.4.3.

---

[github-actions]

🤖 An automated task has requested bottles to be published to this PR.

Caution

Please do not push to this PR branch before the bottle commits have been pushed, as this results in a state that is difficult to recover from. If you need to resolve a merge conflict, please use a merge commit. Do not force-push to this PR branch.