Ettore Di Giacintoandxingyifeng df70ff311d feat: add FunASR speech recognition backend (#10090) ...

Adds FunASR/SenseVoice as a Python backend for speech-to-text with
support for CPU, CUDA 12/13, ROCm, Intel SYCL, L4T, and Apple MPS.

Co-authored-by: xingyifeng <xingyifeng@users.noreply.github.com>

2026-09-11 22:06:26 +00:00

..

agent_collections_param_test.go

fix(agents): URL-decode collection/agent name path params (#10443) (#10471)

2026-06-24 09:42:09 +02:00

agent_collections.go

fix(agents): URL-decode collection/agent name path params (#10443) (#10471)

2026-06-24 09:42:09 +02:00

agent_jobs.go

feat(api): Allow coding agents to interactively discover how to control and configure LocalAI (#9084)

2026-04-04 15:14:35 +02:00

agent_responses.go

feat: add distributed mode (#9124)

2026-03-30 00:47:27 +02:00

agent_skills.go

feat: add distributed mode (#9124)

2026-03-30 00:47:27 +02:00

agents_isolation_test.go

chore: Security hardening (#9719)

2026-05-08 16:25:45 +02:00

agents.go

fix(agents): URL-decode collection/agent name path params (#10443) (#10471)

2026-06-24 09:42:09 +02:00

aliases_test.go

feat(models): model aliases - redirect a model name to another configured model (#10414)

2026-06-20 22:38:42 +02:00

aliases.go

feat(models): model aliases - redirect a model name to another configured model (#10414)

2026-06-20 22:38:42 +02:00

api_instructions_test.go

feat(api): add text moderation endpoint (#11316)

2026-08-03 18:03:46 +02:00

api_instructions.go

feat(audio): list available TTS voices

2026-09-11 21:55:21 +00:00

audio_transform_internal_test.go

fix(audio): reject incompatible transform streams (#11565)

2026-08-18 09:03:16 +02:00

audio_transform.go

fix(audio): reject incompatible transform streams (#11565)

2026-08-18 09:03:16 +02:00

audio.go

security(http): refuse redirects on outbound clients via hardened pkg/httpclient (#10087)

2026-05-30 12:04:10 +02:00

backend_apply_test.go

fix(backends): make backend install ops idempotent unless forced (#10643)

2026-07-02 19:16:29 +02:00

backend_available_cluster_test.go

fix(distributed): backend discovery hid worker-installed backends behind the controller's filesystem (#10967)

2026-07-20 01:09:37 +02:00

backend_load_test.go

feat(realtime): eager blocking pipeline warm-up + /backend/load API (#10662)

2026-07-03 18:00:37 +02:00

backend_load.go

feat(realtime): eager blocking pipeline warm-up + /backend/load API (#10662)

2026-07-03 18:00:37 +02:00

backend_logs_test.go

feat(api): Allow coding agents to interactively discover how to control and configure LocalAI (#9084)

2026-04-04 15:14:35 +02:00

backend_logs.go

feat(api): Allow coding agents to interactively discover how to control and configure LocalAI (#9084)

2026-04-04 15:14:35 +02:00

backend_monitor.go

fix(worker): reap deleted backends and stop models that live on a worker (#10956)

2026-07-20 01:09:22 +02:00

backend_test.go

feat: add FunASR speech recognition backend (#10090)

2026-09-11 22:06:26 +00:00

backend.go

fix(ui): size model fit against the cluster and move node labels into the selector (#11765)

2026-08-28 22:57:35 +02:00

branding_endpoints_test.go

test: add Go + React UI coverage gates and fill test gaps (#9989)

2026-05-26 22:06:10 +02:00

branding_test.go

chore: Security hardening (#9719)

2026-05-08 16:25:45 +02:00

branding.go

chore: Security hardening (#9719)

2026-05-08 16:25:45 +02:00

config_meta_test.go

fix(distributed): keep model replicas config-consistent (#11664)

2026-08-22 22:44:03 +02:00

config_meta.go

fix(distributed): keep model replicas config-consistent (#11664)

2026-08-22 22:44:03 +02:00

cors_proxy_test.go

chore: Security hardening (#9719)

2026-05-08 16:25:45 +02:00

cors_proxy.go

security(http): refuse redirects on outbound clients via hardened pkg/httpclient (#10087)

2026-05-30 12:04:10 +02:00

depth.go

feat(backend): add depth-anything (Depth Anything 3) C++/ggml backend + gallery (#10352)

2026-06-16 16:28:28 +02:00

detection.go

feat(whisper): honor client cancellation via ggml abort_callback (#9710)

2026-05-08 01:44:47 +02:00

detokenize.go

feat(api): add /v1/detokenize endpoint (#9620)

2026-07-30 16:01:47 +02:00

discovery_cluster_capabilities_test.go

fix(distributed): backend discovery hid worker-installed backends behind the controller's filesystem (#10967)

2026-07-20 01:09:37 +02:00

discovery_cluster_installed_test.go

fix(distributed): backend discovery hid worker-installed backends behind the controller's filesystem (#10967)

2026-07-20 01:09:37 +02:00

edit_model_test.go

fix(distributed): resolve config revisions through one entry point

2026-08-24 19:11:16 +00:00

edit_model.go

fix(distributed): keep model replicas config-consistent (#11664)

2026-08-22 22:44:03 +02:00

face_analyze.go

feat(whisper): honor client cancellation via ggml abort_callback (#9710)

2026-05-08 01:44:47 +02:00

face_embed.go

feat(whisper): honor client cancellation via ggml abort_callback (#9710)

2026-05-08 01:44:47 +02:00

face_forget.go

feat(face-recognition): add insightface/onnx backend for 1:1 verify, 1:N identify, embedding, detection, analysis (#9480)

2026-04-22 21:55:41 +02:00

face_identify.go

feat(whisper): honor client cancellation via ggml abort_callback (#9710)

2026-05-08 01:44:47 +02:00

face_register_test.go

feat(faces): replay saved face enrollments (#11908)

2026-09-07 17:40:27 +02:00

face_register.go

feat(faces): replay saved face enrollments (#11908)

2026-09-07 17:40:27 +02:00

face_verify.go

feat(whisper): honor client cancellation via ggml abort_callback (#9710)

2026-05-08 01:44:47 +02:00

finetune.go

fix(ui): size model fit against the cluster and move node labels into the selector (#11765)

2026-08-28 22:57:35 +02:00

gallery.go

fix(galleryop): make admitted operations queryable and survive a failed op (#11044)

2026-07-23 00:02:23 +02:00

get_token_metrics.go

feat(whisper): honor client cancellation via ggml abort_callback (#9710)

2026-05-08 01:44:47 +02:00

images.go

feat(face-recognition): add insightface/onnx backend for 1:1 verify, 1:N identify, embedding, detection, analysis (#9480)

2026-04-22 21:55:41 +02:00

import_model_test.go

Revert "chore(tests): Avoid network, sleep and more during tests" (#11601)

2026-08-19 16:39:39 +02:00

import_model.go

fix(galleryop): make admitted operations queryable and survive a failed op (#11044)

2026-07-23 00:02:23 +02:00

localai_suite_test.go

Revert "chore(tests): Avoid network, sleep and more during tests" (#11601)

2026-08-19 16:39:39 +02:00

mcp_prompts.go

feat(ui): MCP Apps, mcp streaming and client-side support (#8947)

2026-03-11 07:30:49 +01:00

mcp_resources.go

feat(ui): MCP Apps, mcp streaming and client-side support (#8947)

2026-03-11 07:30:49 +01:00

mcp_tools_internal_test.go

fix: Show MCP connection errors in the UI (#11495)

2026-08-13 22:25:58 +02:00

mcp_tools.go

fix: Show MCP connection errors in the UI (#11495)

2026-08-13 22:25:58 +02:00

mcp.go

feat(chat): add end-to-end context compression (#11556)

2026-08-18 11:31:03 +00:00

metrics.go

feat(api): Allow coding agents to interactively discover how to control and configure LocalAI (#9084)

2026-04-04 15:14:35 +02:00

model3d_internal_test.go

feat: Add 3d generation UI/API and trellis2cpp backend (#10979)

2026-07-29 16:15:04 +02:00

model3d_remesh_internal_test.go

feat: Add 3d generation UI/API and trellis2cpp backend (#10979)

2026-07-29 16:15:04 +02:00

model3d_remesh.go

feat: Add 3d generation UI/API and trellis2cpp backend (#10979)

2026-07-29 16:15:04 +02:00

model3d.go

feat: Add 3d generation UI/API and trellis2cpp backend (#10979)

2026-07-29 16:15:04 +02:00

model_load_status_test.go

fix(distributed): run cold model loads as durable jobs instead of holding the advisory lock (#11514)

2026-08-15 13:20:11 +02:00

model_load_status.go

fix(distributed): run cold model loads as durable jobs instead of holding the advisory lock (#11514)

2026-08-15 13:20:11 +02:00

nodes_backends_list_test.go

fix(ci): bound Discord release summaries (#11695)

2026-08-24 09:32:26 +02:00

nodes_install_async_test.go

fix(distributed): make per-node backend upgrade actually upgrade (#10838)

2026-07-15 09:16:55 +02:00

nodes_scheduling_alias_test.go

feat(distributed): key scheduling rules by a model alias (#11771)

2026-08-29 09:16:50 +02:00

nodes_scheduling_test.go

feat(distributed): declarative per-model scheduling via env/args (#10308)

2026-06-13 18:31:06 +02:00

nodes_scheduling_validation_test.go

feat: prefix-cache-aware routing for distributed mode (#10071)

2026-05-30 23:24:22 +02:00

nodes_test.go

fix(distributed): keep model replicas config-consistent (#11664)

2026-08-22 22:44:03 +02:00

nodes_vrambudget_test.go

feat(vram): per-node VRAM allocation budget (LOCALAI_VRAM_BUDGET) (#10833)

2026-07-15 09:58:45 +02:00

nodes.go

feat(nodes): add pluggable routing pipeline

2026-09-11 21:47:08 +00:00

p2p.go

feat(api): Allow coding agents to interactively discover how to control and configure LocalAI (#9084)

2026-04-04 15:14:35 +02:00

pii_test.go

feat(pii): NER tier engine — privacy-filter.cpp backend + NER-centric PII filter (#10360)

2026-06-18 11:45:22 +01:00

pii.go

feat(pii): NER tier engine — privacy-filter.cpp backend + NER-centric PII filter (#10360)

2026-06-18 11:45:22 +01:00

pin_model.go

feat: localai assistant chat modality (#9602)

2026-04-28 19:29:27 +02:00

quantization.go

fix(ui): size model fit against the cluster and move node labels into the selector (#11765)

2026-08-28 22:57:35 +02:00

router_corpus_test.go

feat(router): make KNN a first-class classifier with a persisted, curated corpus (#10652)

2026-08-18 09:37:43 +02:00

router_corpus.go

feat(router): make KNN a first-class classifier with a persisted, curated corpus (#10652)

2026-08-18 09:37:43 +02:00

router_decide_test.go

feat(classifier/VAD): support voice control on low power devices (#10804)

2026-07-29 12:50:22 +02:00

router_decide.go

feat(router): make KNN a first-class classifier with a persisted, curated corpus (#10652)

2026-08-18 09:37:43 +02:00

score.go

feat(middleware): Model routing, PII filtering, Cloud model proxies (#9802)

2026-05-25 09:28:27 +02:00

settings_test.go

fix(pii): load default detectors at startup + add LOCALAI_PII_DEFAULT_DETECTORS (#10474)

2026-06-24 11:08:57 +02:00

settings.go

fix(vram): persist remote probe metadata (#11487)

2026-08-23 08:55:13 +02:00

stores.go

feat(stores): add Valkey Search vector store backend (#11196)

2026-07-29 20:12:29 +02:00

system.go

feat(ui): close the gap between the shipped UI and the design mocks (#11307)

2026-08-03 12:16:09 +02:00

toggle_model_test.go

fix(distributed): keep model replicas config-consistent (#11664)

2026-08-22 22:44:03 +02:00

toggle_model.go

fix(distributed): keep model replicas config-consistent (#11664)

2026-08-22 22:44:03 +02:00

tokenize.go

feat(api): Allow coding agents to interactively discover how to control and configure LocalAI (#9084)

2026-04-04 15:14:35 +02:00

traces_test.go

fix(test): stop the backend-trace specs racing the lossy trace channel (#11146)

2026-07-27 22:38:23 +02:00

traces.go

feat(ui): give Operate and Studio a front door, and fix two layout regressions (#11305)

2026-08-03 00:16:08 +02:00

tts_speed_test.go

fix(tts): forward the OpenAI speed field to the backend (#11097) (#11120)

2026-07-27 19:03:32 +02:00

tts_speed.go

fix(tts): forward the OpenAI speed field to the backend (#11097) (#11120)

2026-07-27 19:03:32 +02:00

tts_voices_test.go

feat(audio): list available TTS voices

2026-09-11 21:55:21 +00:00

tts_voices.go

feat(audio): list available TTS voices

2026-09-11 21:55:21 +00:00

tts.go

feat(tts): support multi-reference personalities

2026-09-11 21:56:08 +00:00

types.go

fix(distributed): keep model replicas config-consistent (#11664)

2026-08-22 22:44:03 +02:00

vad.go

feat(api): Allow coding agents to interactively discover how to control and configure LocalAI (#9084)

2026-04-04 15:14:35 +02:00

video_internal_test.go

feat(backends): add LongCat video and avatar generation (#10792)

2026-07-12 23:58:46 +02:00

video.go

feat(vllm-cpp): serve MiniMax-H3 video+audio generation (#11424)

2026-08-09 22:34:51 +02:00

voice_analyze.go

feat(whisper): honor client cancellation via ggml abort_callback (#9710)

2026-05-08 01:44:47 +02:00

voice_embed.go

feat(whisper): honor client cancellation via ggml abort_callback (#9710)

2026-05-08 01:44:47 +02:00

voice_forget.go

feat: voice recognition (#9500)

2026-04-23 12:07:14 +02:00

voice_identify.go

feat(whisper): honor client cancellation via ggml abort_callback (#9710)

2026-05-08 01:44:47 +02:00

voice_profiles_test.go

feat(tts): support multi-reference personalities

2026-09-11 21:56:08 +00:00

voice_profiles.go

feat(tts): support multi-reference personalities

2026-09-11 21:56:08 +00:00

voice_register.go

feat(whisper): honor client cancellation via ggml abort_callback (#9710)

2026-05-08 01:44:47 +02:00

voice_verify.go

feat(whisper): honor client cancellation via ggml abort_callback (#9710)

2026-05-08 01:44:47 +02:00

vram_test.go

feat(gallery): Speed up load times and clean gallery entries (#9211)

2026-05-06 14:51:38 +02:00

vram.go

feat(gallery): Speed up load times and clean gallery entries (#9211)

2026-05-06 14:51:38 +02:00

welcome.go

feat: add distributed mode (#9124)

2026-03-30 00:47:27 +02:00