Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Python asraudiochineseemotion-recognitionfunasrmcp-servermultilingual-asropenai-compatible-apiparaformerpunctuationpytorchreal-time-asrspeaker-diarizationspeech-recognitionspeech-to-textstreaming-asrtranscriptionvllmvoice-activity-detectionwhisper-alternative
docs: refresh ecosystem operations status
游雁3bc67422d176
diff --git a/docs/community_growth_20k.md b/docs/community_growth_20k.mdindex eebca3784..2965a4e2f 100644--- a/docs/community_growth_20k.md+++ b/docs/community_growth_20k.md@@ -34,14 +34,14 @@ This plan focuses on useful adoption work rather than vanity marketing: if more## Current campaign snapshot-As of 2026-07-13 18:59 UTC, the ecosystem has 35,355 combined GitHub stars, or 4,131 additional stars since the 31,224 baseline. The remaining gap to the +20,000 target is 15,869 stars by 2026-09-30, which requires roughly 201 stars/day across the remaining 79 days.+As of 2026-07-14 04:29 UTC, the ecosystem has 35,366 combined GitHub stars, or 4,142 additional stars since the 31,224 baseline. The remaining gap to the +20,000 target is 15,858 stars by 2026-09-30, which requires roughly 204 stars/day across the remaining 78 days.| Repository | Stars | Forks | Open issues | Open PRs | Last push ||---|---:|---:|---:|---:|---|-| `modelscope/FunASR` | 19,203 | 1,927 | 2 | 0 | 2026-07-13 |-| `FunAudioLLM/Fun-ASR` | 1,392 | 137 | 0 | 0 | 2026-07-13 |-| `FunAudioLLM/SenseVoice` | 8,848 | 793 | 0 | 0 | 2026-07-13 |-| `modelscope/FunClip` | 5,912 | 710 | 0 | 0 | 2026-07-13 |+| `modelscope/FunASR` | 19,213 | 1,928 | 2 | 0 | 2026-07-14 |+| `FunAudioLLM/Fun-ASR` | 1,391 | 137 | 0 | 0 | 2026-07-13 |+| `FunAudioLLM/SenseVoice` | 8,849 | 793 | 0 | 0 | 2026-07-14 |+| `modelscope/FunClip` | 5,913 | 709 | 0 | 0 | 2026-07-13 |Keep this snapshot fresh during weekly planning. The ecosystem mode also reports the remaining gap, days left to 2026-09-30, and the required daily average:@@ -157,11 +157,11 @@ High-star feature requests and roadmap issues are earlier in the funnel than PRs|---|---|---|| `openclaw/openclaw#35835` audio file support in the read tool | Extends a high-visibility agent read path from images to audio, with a natural fallback slot for private OpenAI-compatible STT when the active model cannot consume native audio | Keep native audio attachments separate from transcription fallback: audio-capable models should receive original media, while text-only models can use an explicit `POST /v1/audio/transcriptions` adapter returning transcript plus metadata. FunASR/SenseVoice are useful self-hosted regression backends for that fallback contract. || `openclaw/openclaw#40078` silent preflight transcription in mention-gated channels | Turns voice-note history capture into a high-visibility STT workflow where private transcription can enrich context without triggering assistant replies | Track the proposed `preflightTranscribe` gate: server-side STT should run only after channel/attachment checks, write transcript provenance into history, keep response generation mention-gated, and use an OpenAI-compatible transcription backend so hosted and local FunASR/SenseVoice services share the same contract. |-| `openclaw/openclaw#45508` self-hosted STT/TTS provider support in WebChat | Routes OpenClaw WebChat users toward private OpenAI-compatible STT providers instead of browser-only speech APIs | A batch push-to-talk path has been scoped: browser records a blob, the Gateway calls the configured `tools.media.audio` / OpenAI-compatible transcription backend, and streaming can remain a follow-up. Watch for product/API decisions before proposing code. |+| `openclaw/openclaw#45508` self-hosted STT/TTS provider support in WebChat | Routes OpenClaw WebChat users toward private OpenAI-compatible STT providers instead of browser-only speech APIs | A 2026.6.11 repro exposed a separate managed-room gap. Current main retries `talk.client.create` only for `gateway-relay`, the UI transport factory rejects `managed-room`, `talk.session.appendAudio` rejects managed-room sessions, and `/talk/rooms/...` has no browser media handler. LauraGPT documented the exact control-plane/data-plane boundary at https://github.com/openclaw/openclaw/issues/45508#issuecomment-4965397939. Maintainers must choose a Gateway-relayed STT/TTS media contract or a real room transport before a UI fallback PR can work; keep editable batch dictation in `#98026/#98027` separate. || `openclaw/openclaw#46661` custom ASR server configuration | Connects a 382k-star OpenClaw native voice-input request to self-hosted/private ASR, giving FunASR, SenseVoice, and Qwen3-ASR a clean OpenAI-compatible STT provider path | LauraGPT posted the provider-contract note at https://github.com/openclaw/openclaw/issues/46661#issuecomment-4909572545. Track maintainer decisions on platform default behavior, explicit credential isolation for custom endpoints, multipart `{base_url}/audio/transcriptions`, minimum `{ "text": "..." }` responses, optional segment/timestamp metadata, timeout messaging, and fallback tests before proposing code. || `openclaw/openclaw#87140` pluggable macOS Push-to-Talk STT backend | Opens a native desktop path for FunASR/SenseVoice as local/private ASR behind OpenClaw's existing PTT UX | Keep Apple Speech as the default and watch for a batch-only provider boundary with explicit capability flags (`batch`, `streaming`, `languages`, `local_only`, `requires_network`). || `openclaw/openclaw#98027` editable Control UI dictation | Turns a 382k-star agent UI's ordinary prompt composer into a local/private STT adoption path where FunASR or SenseVoice can sit behind the existing Gateway/media-audio provider boundary | PR is open with `check-docs` failure and missing real microphone -> Gateway -> editable draft proof, so do not call it merge-ready. LauraGPT posted the downstream ASR contract checklist at https://github.com/openclaw/openclaw/pull/98027#issuecomment-4911740942; track whether proof covers local/private transcription provider dispatch, no auto-send, redacted errors, and temp-audio cleanup on success/failure. |-| `openclaw/openclaw#102028` QQBot speech transcription timeout | Hardens a very high-visibility voice-message transcription path so stalled hosted or self-hosted STT providers do not block inbound QQBot attachments indefinitely | PR is open and behind main while checks continue; LauraGPT posted a non-blocking self-hosted STT contract note at https://github.com/openclaw/openclaw/pull/102028#issuecomment-4911671891. Track whether the timeout remains configurable through the public provider/audio model path and whether timeout errors stay distinguishable from auth/model/route errors for slow FunASR/SenseVoice endpoints. |+| `openclaw/openclaw#102028` QQBot speech transcription timeout | Hardens a very high-visibility voice-message transcription path so stalled hosted or self-hosted STT providers do not block inbound QQBot attachments indefinitely | Merged on 2026-07-09 as `64e80888d4da955f38461b1f669f105c03adc952`. LauraGPT's non-blocking self-hosted STT contract note remains at https://github.com/openclaw/openclaw/pull/102028#issuecomment-4911671891; treat this as a completed downstream hardening win and watch release behavior for distinguishable timeout versus auth/model/route errors. || `NousResearch/hermes-agent#56989` local STT docs and hardening | Helps self-hosted messaging gateways document fully local voice-note transcription for private deployments | Track whether docs define a backend-neutral `local_command` and local HTTP contract; FunASR/SenseVoice should fit as wrappers or OpenAI-compatible `/v1/audio/transcriptions` services. || `NousResearch/hermes-agent#16185` Telegram voice-message STT provider precedence | Turns Telegram voice notes in a high-visibility messaging agent into a direct local/private STT adoption path, where FunASR/SenseVoice can fit through either `local_command` wrappers or OpenAI-compatible transcription servers | Fresh user report says removing the OpenAI STT block made local STT work, suggesting provider precedence/config resolution rather than model failure. LauraGPT posted the backend-neutral provider-boundary checklist at https://github.com/NousResearch/hermes-agent/issues/16185#issuecomment-4911698678; track for a Telegram adapter or gateway fix that logs the selected provider and prevents silent OpenAI fallback. || `NousResearch/hermes-agent#60624` Windows ffmpeg discovery for Discord voice | Removes a Windows setup blocker in a high-visibility Discord voice transcription/TTS path before local/private STT providers such as FunASR/SenseVoice can work reliably | PR `NousResearch/hermes-agent#60627` now uses one shared `FFMPEG_PATH` / PATH / winget resolver for receiver conversion, legacy playback, and voice-FX mixer decoding. LauraGPT addressed and resolved the maintainer review on 2026-07-13 UTC; head `0760d751` is mergeable with 210 related tests passing and no unresolved review threads. No GitHub checks have been emitted yet, so wait for CI and maintainer review without another status ping. |@@ -170,7 +170,9 @@ High-star feature requests and roadmap issues are earlier in the funnel than PRs| `Tencent/ncnn#6790` Qwen3-ASR ncnn port and multi-platform deployment | Opens a 23k-star mobile/edge inference path for Qwen3-ASR-style local transcription, where successful conversion can feed Fun-ASR-Nano/Qwen3-ASR users looking for lightweight on-device ASR | This is a 2026 Rhino-Bird activity issue, so LauraGPT posted a non-claim technical validation note rather than trying to own the task: https://github.com/Tencent/ncnn/issues/6790#issuecomment-4912104458. Watch for a public `Qwen3-ASR-ncnn` repo or PR, then verify PyTorch parity on fixed preprocessing, normalized CJK text, module-level encoder/projector/decoder drift, and Linux/Windows smoke commands. || `Wei-Shaw/sub2api#3754` OpenAI audio endpoint passthrough | Adds a Chinese gateway path for OpenAI-compatible STT/TTS clients and self-hosted FunASR/SenseVoice endpoints | Watch for standard multipart `POST /v1/audio/transcriptions` passthrough, language/model forwarding, and a CJK regression that preserves `language=zh`. || `elizaOS/eliza#14807` audio PII redaction pipeline | Makes timed ASR spans part of an agent safety workflow where local CJK/private transcription can be useful | Keep FunASR/SenseVoice positioned as optional verifier backends; avoid coupling the primary redaction path to one ASR engine. |-| `modelcontextprotocol/servers#4299` FunASR speech-to-text MCP server | Keeps FunASR visible in the canonical MCP server discussion for local speech tools used by Claude/Cursor-style clients | The compact upstream server now exists in `examples/mcp_server` with `transcribe_audio`, Dockerfile, `glama.json`, and stdio smoke evidence. LauraGPT posted the upstream-status update at https://github.com/modelcontextprotocol/servers/issues/4299#issuecomment-4901476584; next action is to track whether MCP maintainers prefer an external community-server reference instead of vendoring. |+| `modelcontextprotocol/servers#4299` FunASR speech-to-text MCP server | Keeps FunASR visible in the canonical MCP server discussion for local speech tools used by Claude/Cursor-style clients | The compact upstream server now exists in `examples/mcp_server` with `transcribe_audio`, Dockerfile, and `glama.json`. FunASR PR `#3216` fixed the custom `Content-Length` framing in favor of standard newline-delimited MCP stdio and merged as `3b146a344d3b744f2d7d89ca32a593af820cc605`; regression coverage verifies official SDK `initialize`, `tools/list`, and `tools/call`. Glama accepted the repository submission for review on 2026-07-14, while its public API and score badge remain unpublished. |+| `zhouxiaoka/autoclip#67` SenseVoice subtitle timestamp quality | Fixes a visible SenseVoice integration where aligned word timestamps are collapsed into unusably long subtitle cues | LauraGPT reproduced the branch behavior with FunASR 1.3.14: a 5.55-second clip returned 20 aligned words but became one cue, while the exact 45.1-second CAM++ path returned 142 word timestamps but prioritized two `sentence_info` spans of roughly 30 and 15 seconds. Root-cause evidence and the fix contract are at https://github.com/zhouxiaoka/autoclip/issues/67#issuecomment-4965349491: request `output_timestamp=True`, group word timestamps by punctuation/length/duration, use `sentence_info` only as fallback, and avoid loading CAM++ for plain subtitles. Wait for owner feedback before opening code. |+| `deepset-ai/haystack-core-integrations#3572` FunASR-Haystack Python 3.14 installation | Removes an installation scare in Haystack's integration catalog that can prevent new users from trying FunASR | A current Windows CPython 3.14 resolver check succeeds with `funasr 1.3.14`, `umap-learn 0.5.12`, `pynndescent 0.6.0`, `numba 0.66.0`, and `llvmlite 0.48.0`; the reported `llvmlite 0.36.0` path is therefore more consistent with a stale lock or lagging package index than the current dependency graph. Diagnostic commands and requested lock/index evidence are at https://github.com/deepset-ai/haystack-core-integrations/issues/3572#issuecomment-4965365012. Do not change core packaging until the reporter provides a current failing resolution. || `crewAIInc/crewAI#5983` FunASR for voice-enabled agents | Routes a 55k-star multi-agent framework toward a provider-neutral voice command path where FunASR/SenseVoice can be a local OpenAI-compatible transcription backend | LauraGPT revived the stale broad request with a concrete `voice.stt.*` config, multipart `/v1/audio/transcriptions` contract, mock endpoint test shape, and agent-command handoff at https://github.com/crewAIInc/crewAI/issues/5983#issuecomment-4901293351. Watch for maintainer direction before opening a code PR. || `Significant-Gravitas/AutoGPT#13347` FunASR as an open-source STT backend | Keeps the 185k-star AutoGPT voice-input discussion anchored on a generic OpenAI-compatible transcription contract rather than a heavyweight FunASR-only dependency | LauraGPT first mapped the existing hard-coded Copilot Whisper route, then opened draft PR `Significant-Gravitas/AutoGPT#13500` and linked it back at https://github.com/Significant-Gravitas/AutoGPT/issues/13347#issuecomment-4908286807. Track whether maintainers prefer env-based `/v1/audio/transcriptions` configurability, a workflow block, or a separate self-hosted transcript pipeline. || `chatchat-space/Langchain-Chatchat#5479` FunASR/SenseVoice voice input | Puts FunASR in a 38k-star Chinese RAG/Agent app where local audio upload can feed existing Chat and knowledge-base flows | LauraGPT proposed an OpenAI-compatible ASR endpoint slice, including `asr.base_url`, multipart request shape, minimal `{ "text": "..." }` response, and mocked CI endpoint at https://github.com/chatchat-space/Langchain-Chatchat/issues/5479#issuecomment-4901293565. Monitor stale handling and maintainer appetite for a first audio-upload transcription path. |@@ -200,7 +202,7 @@ High-star feature requests and roadmap issues are earlier in the funnel than PRs| `OpenBMB/VoxCPM#349` Windows CUDA installer with SenseVoice fallback | Puts SenseVoice into a 32k-star multilingual TTS app's Windows install and first-run ASR path as the fallback when local Parakeet/CUDA is unavailable | Current head `9f34141cc81e04028c4e62ac652f2a66dd453dfa` is dirty only in `app.py`; LauraGPT posted the conflict recipe and light validation at https://github.com/OpenBMB/VoxCPM/pull/349#issuecomment-4905293176. Wait for author rebase or maintainer action without duplicate comments. || `livekit/agents#6176` FunASR/SenseVoice realtime STT plugin | Opens a path into LiveKit's realtime voice-agent ecosystem where local STT is evaluated alongside hosted providers | CI and CLA are green; avoid duplicate pings and monitor for maintainer review on plugin scope, package metadata, or optional dependency expectations. || `datajuicer/data-juicer#938` HumanVBench audio/video operators | Places FunASR/SenseVoice-style speech understanding into a 6k-star data processing toolkit used to evaluate human-centric video and multimodal datasets | Current PR is open and mergeable but process-blocked while unit-test jobs are still waiting; LauraGPT posted the FunASR/SenseVoice dependency and validation follow-up at https://github.com/datajuicer/data-juicer/pull/938#issuecomment-4905235851. Wait for CI or maintainer feedback before adding more comments. |-| `punkpeye/awesome-mcp-servers#7153` FunASR MCP server listing | Exposes FunASR to a high-star MCP discovery list used by agent-tool builders looking for local speech tools | Glama manifest now points at the current `server.json` schema and declares the maintainer for verification; the MCP Dockerfile also carries the official Registry OCI ownership label. Next step is maintainer OAuth/Glama ingestion or a public OCI image plus matching MCP Registry `server.json`, then update the external PR only after a valid score badge or maintainer feedback. |+| `punkpeye/awesome-mcp-servers#7153` FunASR MCP server listing | Exposes FunASR to a high-star MCP discovery list used by agent-tool builders looking for local speech tools | Head `e5f210150a4e` is clean and mergeable, and both `check-submission` runs are green. After the merged MCP stdio fix passed official-SDK introspection and tool-call tests, Glama accepted `modelscope/FunASR` for review on 2026-07-14. The API and score badge still return 404 while review is pending, so leave the badge out until the listing is public; the current evidence update is https://github.com/punkpeye/awesome-mcp-servers/pull/7153#issuecomment-4965257590. || `zts212653/clowder-ai#1083` Qwen3-ASR service unification | Puts Qwen3-ASR into a user-facing local STT service slot by making it a `whisper-stt` backend variant instead of a separate, easier-to-misconfigure service | Head `28067864e313cd03dd3d6f4ce0a72ec5b5026b47` reports green CI after fixes for Rosetta hardware detection, Qwen3-ASR install/server dispatch, async backend locking, temp WAV cleanup, and stale setup docs; author status update: https://github.com/zts212653/clowder-ai/pull/1083#issuecomment-4910797452. Wait for maintainer re-review without duplicate comments. || `run-llama/llama_index#21958` FunASR endpoint reader | Puts FunASR behind a LlamaIndex reader for OpenAI-compatible transcription endpoints used in RAG and agent pipelines | LauraGPT rechecked head `07a8599deaebe5e7a559d62174e7a872870c2f7e` at https://github.com/run-llama/llama_index/pull/21958#issuecomment-4905345545; author acknowledged the shared-reader pytest caveat at https://github.com/run-llama/llama_index/pull/21958#issuecomment-4905384536. Keep the endpoint contract clear and avoid forcing local `funasr` dependencies into the main package. || `run-llama/llama_index#21996` local FunASR reader | Gives LlamaIndex users a local SenseVoice/FunASR reader for private transcription workflows | Keep optional dependencies isolated, verify the reader does not affect default installs, and watch for maintainer guidance on package extras. |@@ -212,7 +214,7 @@ High-star feature requests and roadmap issues are earlier in the funnel than PRs| `getpaseo/paseo#313` FunASR streaming STT provider | Adds a standalone FunASR/SenseVoice server and streaming dictation provider to a 10k-star agent orchestration app | Current head `19d9270f1b55d5a0d59288ff2c4a4e707bd60c9a` is dirty against main; LauraGPT triage at https://github.com/getpaseo/paseo/pull/313#issuecomment-4905606566 documents the conflict set and a `needsFunASR` provider-wiring bug to fix during rebase. Wait for author rebase or maintainer guidance without duplicate pings. || `getpaseo/paseo#1634` SenseVoice local STT model support | Adds SenseVoice to a local voice/dictation app with a visible offline STT model catalog and speech CLI path | Current PR is mergeable at head `4cc65ac6fbc9735ac487648bbbd02ee487050f31`; posted focused local validation at https://github.com/getpaseo/paseo/pull/1634#issuecomment-4905550193 covering server deps build, format check, 3 speech Vitest files with 10 tests, and server build. Wait for maintainer review without duplicate pings. || `getpaseo/paseo#2044` SenseVoice, Paraformer, and multilingual Kokoro local speech models | Makes Chinese and multilingual local speech a first-class default in a 10k-star agent orchestration app instead of requiring an English-only Parakeet/Kokoro setup | Head `99e43e731dd6` is mergeable and Greptile is green, but no code test workflow ran and the PR adds no tests. LauraGPT reviewed the upstream sherpa-onnx config shapes and posted the remaining model-selection, test, and documentation requirements at https://github.com/getpaseo/paseo/pull/2044#pullrequestreview-4688090003: normalize BCP 47 tags such as `zh-CN`/`pt-BR` before catalog matching, cover Chinese defaults and explicit overrides, and update the stale local-model list in `docs/data-model.md`. One current review thread remains; wait for the author update. |-| `infiniflow/ragflow#16473` FunASR / SenseVoice STT provider | Adds FunASR to a high-star RAG workflow product where local STT can become a visible configuration choice | Rebased the five-commit integration from a branch point 289 upstream commits behind onto `main@466f33e6`; head `173f88658817` is mergeable with a clean state. `range-diff` shows no semantic PR change, the mocked OpenAI-client provider contract passed, the focused Markdown suite reports 12 passed, and the three visible repository workflow jobs are skipped rather than failed. CodeRabbit accepted a fresh review request without new actionable findings; evidence is at https://github.com/infiniflow/ragflow/pull/16473#issuecomment-4956444898. |+| `infiniflow/ragflow#16473` FunASR / SenseVoice STT provider | Adds FunASR to a high-star RAG workflow product where local STT can become a visible configuration choice | The integration is now one focused commit at head `7aa7512e881f`, clean and mergeable. Focused backend tests (7 passed), frontend tests (2 passed), Ruff, ESLint, Prettier, JSON validation, and `git diff --check` passed; CodeRabbit is green. Backend reviewer `Lynn-Inf` reported LGTM and frontend reviewer `dcc123456` formally approved the current head on 2026-07-14. Wait for merge without another status ping. || `infiniflow/ragflow#16844` Fun-ASR-Flash Tongyi-Qianwen provider | Places the hosted Fun-ASR-Flash model in an 84k-star RAG product while keeping existing Qwen audio behavior intact | Head `bf1bb382f452` is clean and mergeable. The author fixed MIME/URL format inference and removed inaccurate hard-coded sample-rate metadata; one current thread remains for the 10 MB Base64 input limit on local files. LauraGPT provided the official-documentation boundary, allocation-free encoded-size check, actionable URL fallback error, and focused boundary-test scope at https://github.com/infiniflow/ragflow/pull/16844#issuecomment-4956465917; wait for the contributor update. || `Open-Less/openless#793` Fun-ASR-Flash and unified Bailian ASR support | Adds Fun-ASR-Flash to a desktop AI client while consolidating hosted ASR configuration, exposing the model to users already selecting Qwen and Bailian providers | Head `5f4078b31b8a` is mergeable with all five checks green. LauraGPT submitted three official-documentation-backed blockers at https://github.com/Open-Less/openless/pull/793#pullrequestreview-4688035289: do not route `fun-asr-flash-8k-realtime*` WebSocket models into the batch HTTP API, preserve Singapore/workspace endpoint configuration instead of forcing the China public host, and do not inject the realtime-only `vocabulary_id` into Fun-ASR-Flash sync requests. All three threads are current and unanswered; wait for the author fix without duplicate comments. || `mudler/LocalAI#10090` FunASR backend | Exposes FunASR through a high-star local AI engine used by self-hosters and edge deployments | Upstream DCO is green; the fork-side `tests` failure is a CodeQL/SARIF upload permission gate on a fork, not a FunASR backend regression. Local CPU smoke validation remains `backend/python/funasr/test.py` with four passing tests, so wait for maintainer-side review or rerun without duplicate pings. |