wip

2026-07-26 11:58:53 +00:00 · 2026-05-19 18:35:25 +02:00
parent ec67a12fe4
commit de3764391d
8 changed files with 484 additions and 20 deletions
@@ -335,7 +335,8 @@ services:
  multi-user-transcriber:
    build:
      context: ./src/agents
-      target: development
+      target: development    
+    command: ["python", "multi_user_transcriber.py", "dev"]
    env_file:
      - env.d/development/multi_user_transcriber
    volumes:
@@ -23,7 +23,10 @@ from livekit.agents import (
 from livekit.agents import (
    room_io as lk_room_io,
 )
-from livekit.plugins import deepgram, silero
+from livekit.plugins import deepgram, mistralai, silero
+from mistralai.client import Mistral
+
+import voxtral_vllm_stt

 load_dotenv()

@@ -46,6 +49,23 @@ def create_stt_provider():
        )
    elif STT_PROVIDER == "kyutai":
        _stt_instance = kyutai.STT(base_url=os.getenv("KYUTAI_STT_BASE_URL"))
+    elif STT_PROVIDER == "voxtral-realtime":
+        client = Mistral(
+            api_key=os.getenv("VOXTRAL_REALTIME_STT_API_KEY"),
+            server_url=os.getenv("VOXTRAL_REALTIME_STT_BASE_URL"),
+        )
+        _stt_instance = mistralai.STT(
+            client=client,
+            model=os.getenv(
+                "VOXTRAL_STT_MODEL",
+                "voxtral-mini-transcribe-realtime-2602",
+            ),
+        )
+    elif STT_PROVIDER == "voxtral-vllm":
+        # The plugin resolves base_url / model / api_key from the environment
+        # itself (with sensible defaults). Passing os.getenv(...) directly would
+        # forward an explicit None for unset vars, which defeats that fallback.
+        _stt_instance = voxtral_vllm_stt.STT()
    else:
        raise ValueError(f"Unknown STT_PROVIDER: {STT_PROVIDER}")

@@ -4,8 +4,9 @@ name = "agents"
 version = "1.15.0"
 requires-python = ">=3.12"
 dependencies = [
-    "livekit-agents==1.4.5",
+    "livekit-agents>=1.4.5",
    "livekit-plugins-deepgram==1.4.5",
+    "livekit-plugins-mistralai==1.5.4",
    "livekit-plugins-silero==1.4.5",
    "livekit-plugins-kyutai-lasuite==0.0.6",
    "python-dotenv==1.2.2",
@@ -15,6 +15,7 @@ dependencies = [
    { name = "livekit-agents" },
    { name = "livekit-plugins-deepgram" },
    { name = "livekit-plugins-kyutai-lasuite" },
+    { name = "livekit-plugins-mistralai" },
    { name = "livekit-plugins-silero" },
    { name = "minio" },
    { name = "protobuf" },
@@ -28,9 +29,10 @@ dev = [

 [package.metadata]
 requires-dist = [
-    { name = "livekit-agents", specifier = "==1.4.5" },
+    { name = "livekit-agents", specifier = ">=1.4.5" },
    { name = "livekit-plugins-deepgram", specifier = "==1.4.5" },
    { name = "livekit-plugins-kyutai-lasuite", specifier = "==0.0.6" },
+    { name = "livekit-plugins-mistralai", specifier = "==1.5.4" },
    { name = "livekit-plugins-silero", specifier = "==1.4.5" },
    { name = "minio", specifier = "==7.2.15" },
    { name = "protobuf", specifier = "==6.33.5" },
@@ -729,9 +731,18 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/da/e9/1f9ada30cef7b05e74bb06f52127e7a724976c225f46adb65c37b1dadfb6/jiter-0.14.0-graalpy312-graalpy250_312_native-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:67f00d94b281174144d6532a04b66a12cb866cbdc47c3af3bfe2973677f9861a", size = 349613, upload-time = "2026-04-10T14:28:40.066Z" },
 ]

+[[package]]
+name = "jsonpath-python"
+version = "1.1.6"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/98/18/4ca8742534a5993ff383f7602e325ce2d5d7cc93d72ac5e1cdedbea8a458/jsonpath_python-1.1.6.tar.gz", hash = "sha256:dded9932b4ec41fb8726e09c83afa4e6be618f938c2db287cc2a81723c639671", size = 88178, upload-time = "2026-05-07T01:26:34.482Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/55/8a/1270a6803bd821cbfcdda387eaa13cb41a7b1f7b9bd145979b3bfb9d6cb7/jsonpath_python-1.1.6-py3-none-any.whl", hash = "sha256:a1c50afd8d3fbbaf47a4873bc890dcb3c15da96f5c020327977d844d8731a2d4", size = 14453, upload-time = "2026-05-07T01:26:33.306Z" },
+]
+
 [[package]]
 name = "livekit"
-version = "1.1.2"
+version = "1.1.7"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
    { name = "aiofiles" },
@@ -739,18 +750,18 @@ dependencies = [
    { name = "protobuf" },
    { name = "types-protobuf" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/9c/9c/0a9b9e1f88226df372b9ccc58868ce9a1eb97c8bf5257463a643dda2a6da/livekit-1.1.2.tar.gz", hash = "sha256:ef826e94dd039767fcabc2f0d810b1b2335c9cf249f52320b6ab018b06d5ccd7", size = 320006, upload-time = "2026-02-17T01:18:46.828Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/e1/1e/3ad724abacb6514fc64c7b4a8c82a41780cbc82baee621b8dcc92dded005/livekit-1.1.7.tar.gz", hash = "sha256:29e5f13e2639c041f18e29d1066019a6380031391b6363509f06e3dbef8426a6", size = 332704, upload-time = "2026-04-27T13:49:48.432Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/07/7b/1b2d448d8976b14794bfba3d003e1451c79afa77e6b9fa1593f19175ef90/livekit-1.1.2-py3-none-macosx_10_15_x86_64.whl", hash = "sha256:78be23f3f6315354aaacee664eb19b793009bc06faa8184ad9c07cffbe8d7f74", size = 9844157, upload-time = "2026-02-17T01:18:34.036Z" },
-    { url = "https://files.pythonhosted.org/packages/f9/fb/19f7fc4a7df3b1385ba2e32b907c5a502fe01c10e6ee2fb76629c068667d/livekit-1.1.2-py3-none-macosx_11_0_arm64.whl", hash = "sha256:656f4d9e4692f3d7ab2e51b0bbf4ec03b356a487b7ff220576dab496e60f99f3", size = 8651703, upload-time = "2026-02-17T01:18:36.416Z" },
-    { url = "https://files.pythonhosted.org/packages/29/59/ac6a3987bfd11687f86156627a8c7f6a0047a72877748facbd427e63b157/livekit-1.1.2-py3-none-manylinux_2_28_aarch64.whl", hash = "sha256:a20e681d8a4929e27df69f818888ae649700c9d52a262abbec296c84937bc337", size = 14085891, upload-time = "2026-02-17T01:18:38.561Z" },
-    { url = "https://files.pythonhosted.org/packages/0a/a5/680548ef7bf5034144ae01f1f742a6c49e4428942b3119ac6553207fea9b/livekit-1.1.2-py3-none-manylinux_2_28_x86_64.whl", hash = "sha256:0e4d8105a0c317b513a118b48340b5773239103cb6305768451ef99ac7567823", size = 11448902, upload-time = "2026-02-17T01:18:42.006Z" },
-    { url = "https://files.pythonhosted.org/packages/00/05/e484f8fc079c5de7690e58ed48f44e77436b8732c3050da742bdfca51a5c/livekit-1.1.2-py3-none-win_amd64.whl", hash = "sha256:dd4a436fa16de589353bfbabde91068ab64241afd05b04f21fb1f22bfe155dc0", size = 10394562, upload-time = "2026-02-17T01:18:44.589Z" },
+    { url = "https://files.pythonhosted.org/packages/fd/f8/176fe3d5569ed03b2c60991f4a90edfd2421a5ad0c4a9a70974d409b3329/livekit-1.1.7-py3-none-macosx_10_15_x86_64.whl", hash = "sha256:26df0760e9b9d3eeb0d773614bc344b6aae7d37c60a9b0c93b1c58dcb6bb2f6b", size = 10127354, upload-time = "2026-04-27T13:49:35.805Z" },
+    { url = "https://files.pythonhosted.org/packages/29/f2/05bd6f3729ecb564ddc9052afc43c3b9e39a43d24f7821946bc78a5dddd2/livekit-1.1.7-py3-none-macosx_11_0_arm64.whl", hash = "sha256:e49e79d39b2c74104c377b6e3cb789d47dd92cb993327234966c41f19df28292", size = 8954208, upload-time = "2026-04-27T13:49:38.359Z" },
+    { url = "https://files.pythonhosted.org/packages/58/32/99f52a9c71dcc3b3370783ad427e5974b9491948b6d9beb5b3f933df8f1e/livekit-1.1.7-py3-none-manylinux_2_28_aarch64.whl", hash = "sha256:c3db851f510edac945b9bc402f6629d5969b4f3252e8d0b24dd158d9e9a5485d", size = 9962579, upload-time = "2026-04-27T13:49:40.28Z" },
+    { url = "https://files.pythonhosted.org/packages/bf/9e/53768dd73f1ce2d3eff7d6c1d87c3531f795c57880a3b51eb5cee1aec6fa/livekit-1.1.7-py3-none-manylinux_2_28_x86_64.whl", hash = "sha256:6c227e2f840aa547224e2fbd45f953c8a0b30939a18e1d56deca8c4268c95804", size = 11355003, upload-time = "2026-04-27T13:49:42.881Z" },
+    { url = "https://files.pythonhosted.org/packages/42/55/2c68732dbcdb3fc1a58592db27697c6d27e2f77ade7eaeb818e88637020b/livekit-1.1.7-py3-none-win_amd64.whl", hash = "sha256:3b0bcc48430cb2138eade01f6b59ddd3be1c1e90f6c251291d0dd4dc1623fc0d", size = 10696832, upload-time = "2026-04-27T13:49:46.362Z" },
 ]

 [[package]]
 name = "livekit-agents"
-version = "1.4.5"
+version = "1.5.8"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
    { name = "aiofiles" },
@@ -782,9 +793,9 @@ dependencies = [
    { name = "typing-extensions" },
    { name = "watchfiles" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/9c/06/1a23902ffea2742e60e30f957f3a96766be125892a2573ea1754051b3d8d/livekit_agents-1.4.5.tar.gz", hash = "sha256:19fdf45a2c4d02d86b4ad132b73bf3f58eadb75f79819e5015e6fadfb1263852", size = 2416100, upload-time = "2026-03-11T06:45:03.912Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/bb/23/8af550199aef211304290596c1ce073de9ac22d6b2beea51ca362d70b2eb/livekit_agents-1.5.8.tar.gz", hash = "sha256:ab8951fb7a4f79f81c13f962a401a76c9ecbcb79c9ebd5cad5f0554062b70b6d", size = 2494457, upload-time = "2026-05-05T18:46:42.965Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/71/ad/a7613ddd5cfb29e015913ae44b804505d41c1d02d19ffeaf2f7015d23664/livekit_agents-1.4.5-py3-none-any.whl", hash = "sha256:aff0b61dbd24b1a100cccca8e2a0056f414b861ce71ba8e4338bc5f89e149f7a", size = 2499369, upload-time = "2026-03-11T06:45:01.772Z" },
+    { url = "https://files.pythonhosted.org/packages/37/1e/3f5e2580f9ffdb5267a7c9be003f8f711ea58c4e0764a74999c800ed3d0e/livekit_agents-1.5.8-py3-none-any.whl", hash = "sha256:737a2d517cf2d6c1d22221d720ed12fcd47a21019abb4b5b20533407b57bb9ea", size = 2594846, upload-time = "2026-05-05T18:46:40.156Z" },
 ]

 [package.optional-dependencies]
@@ -862,6 +873,19 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/af/65/2db9ec521718827960a8bc99dd9ff12534a27b0fbf60aee2d3160000d11c/livekit_plugins_kyutai_lasuite-0.0.6-py3-none-any.whl", hash = "sha256:e8b9b862c950c4ed8b13a8229735f081807b9fbd8a04f2914abb3c05e5745528", size = 6442, upload-time = "2025-12-28T21:11:59.435Z" },
 ]

+[[package]]
+name = "livekit-plugins-mistralai"
+version = "1.5.4"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "livekit-agents" },
+    { name = "mistralai", extra = ["realtime"] },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/14/c0/c7e748735583a14cbece58838bf648c00577eb356a9cf4c827fe21d14ebe/livekit_plugins_mistralai-1.5.4.tar.gz", hash = "sha256:3801e861142d16a748cd3dec535830741f6b657937e6193cc15d7fe20ed68e81", size = 10999, upload-time = "2026-04-16T04:52:09.88Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/20/05/e55ef9c3049609425f96e5e450a77f30358a172c0c5480b2cc6eb89ec18c/livekit_plugins_mistralai-1.5.4-py3-none-any.whl", hash = "sha256:2148e18cb418b7f07fe8bf975b2c7fbb6e9437e501646f8fbd4c077e59c5d135", size = 13040, upload-time = "2026-04-16T04:52:08.723Z" },
+]
+
 [[package]]
 name = "livekit-plugins-silero"
 version = "1.4.5"
@@ -878,15 +902,15 @@ wheels = [

 [[package]]
 name = "livekit-protocol"
-version = "1.1.6"
+version = "1.1.8"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
    { name = "protobuf" },
    { name = "types-protobuf" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/5b/28/8a7ee5a4126476a0ce770a482274d51fc81ae0d9f578c07f07d6655acfc4/livekit_protocol-1.1.6.tar.gz", hash = "sha256:43648863440a6ce064f7f8b8b287dda8f5ac82b8da64738b20f42cad51e70f9b", size = 93925, upload-time = "2026-04-20T15:48:43.032Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/6b/17/761372e1db01925bda77c679ffde19a9d128a4ba53d864dc50a0a9f93ce8/livekit_protocol-1.1.8.tar.gz", hash = "sha256:b3850c09847d54aaa538c87a90ffb5cf267123a0725f2b03874e39e88fc59ccb", size = 98588, upload-time = "2026-05-05T09:12:33.171Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/76/36/525cd9364036617aa97c597c93d7bddb6be311b86288cd54de77e4892544/livekit_protocol-1.1.6-py3-none-any.whl", hash = "sha256:286ac0bd555b6b75cd8a0c5d417572d7dab524129fcea43080202d170f957710", size = 115012, upload-time = "2026-04-20T15:48:41.312Z" },
+    { url = "https://files.pythonhosted.org/packages/6d/54/fca19cd45d0c74bb5ef88b0257cf594ec5549192a15957dd22596acdec32/livekit_protocol-1.1.8-py3-none-any.whl", hash = "sha256:dc379b3e713dc8d8642f694c72d9a38b41220f05b2ce8fc6662f445d20953c17", size = 121119, upload-time = "2026-05-05T09:12:31.787Z" },
 ]

 [[package]]
@@ -926,6 +950,30 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/fb/6f/3690028e846fe432bfa5ba724a0dc37ec9c914965b7733e19d8ca2c4c48d/minio-7.2.15-py3-none-any.whl", hash = "sha256:c06ef7a43e5d67107067f77b6c07ebdd68733e5aa7eed03076472410ca19d876", size = 95075, upload-time = "2025-01-19T08:57:24.169Z" },
 ]

+[[package]]
+name = "mistralai"
+version = "2.4.5"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "eval-type-backport" },
+    { name = "httpx" },
+    { name = "jsonpath-python" },
+    { name = "opentelemetry-api" },
+    { name = "opentelemetry-semantic-conventions" },
+    { name = "pydantic" },
+    { name = "python-dateutil" },
+    { name = "typing-inspection" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/8e/3f/5624d57c5897c83c55d3e4c7dd4127de42ad14fd3183e26566cdc7dca1bf/mistralai-2.4.5.tar.gz", hash = "sha256:ef165bb004ec4423cbf19a440bf0983ca0c3fc92ab12a35ebca097bdf418e33a", size = 424611, upload-time = "2026-05-07T11:46:43.888Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/1b/48/2c5c4f853dec32a625c1a3d23809b80cf2e135c3441fe1764f72910dfea9/mistralai-2.4.5-py3-none-any.whl", hash = "sha256:bf3b6550258ab16dec8547b90e9c18bebf9099f55b7fc25a884bf0bbeffced0f", size = 995999, upload-time = "2026-05-07T11:46:41.915Z" },
+]
+
+[package.optional-dependencies]
+realtime = [
+    { name = "websockets" },
+]
+
 [[package]]
 name = "mpmath"
 version = "1.3.0"
@@ -1605,6 +1653,18 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/e5/7a/8dd906bd22e79e47397a61742927f6747fe93242ef86645ee9092e610244/pyjwt-2.12.1-py3-none-any.whl", hash = "sha256:28ca37c070cad8ba8cd9790cd940535d40274d22f80ab87f3ac6a713e6e8454c", size = 29726, upload-time = "2026-03-13T19:27:35.677Z" },
 ]

+[[package]]
+name = "python-dateutil"
+version = "2.9.0.post0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "six" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/66/c0/0c8b6ad9f17a802ee498c46e004a0eb49bc148f2fd230864601a86dcf6db/python-dateutil-2.9.0.post0.tar.gz", hash = "sha256:37dd54208da7e1cd875388217d5e00ebd4179249f90fb72437e91a35459a0ad3", size = 342432, upload-time = "2024-03-01T18:36:20.211Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/ec/57/56b9bcc3c9c6a792fcbaf139543cee77261f3651ca9da0c93f5c1221264b/python_dateutil-2.9.0.post0-py2.py3-none-any.whl", hash = "sha256:a8b2bc7bffae282281c8140a97d3aa9c14da0b136dfe83f850eea9a5f7470427", size = 229892, upload-time = "2024-03-01T18:36:18.57Z" },
+]
+
 [[package]]
 name = "python-dotenv"
 version = "1.2.2"
@@ -1676,6 +1736,15 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/e0/f9/0595336914c5619e5f28a1fb793285925a8cd4b432c9da0a987836c7f822/shellingham-1.5.4-py2.py3-none-any.whl", hash = "sha256:7ecfff8f2fd72616f7481040475a65b2bf8af90a56c89140852d1120324e8686", size = 9755, upload-time = "2023-10-24T04:13:38.866Z" },
 ]

+[[package]]
+name = "six"
+version = "1.17.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/94/e7/b2c673351809dca68a0e064b6af791aa332cf192da575fd474ed7d6f16a2/six-1.17.0.tar.gz", hash = "sha256:ff70335d468e7eb6ec65b95b99d3a2836546063f63acc5171de367e834932a81", size = 34031, upload-time = "2024-12-04T17:35:28.174Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/b7/ce/149a00dd41f10bc29e5921b496af8b574d8413afcd5e30dfa0ed46c2cc5e/six-1.17.0-py2.py3-none-any.whl", hash = "sha256:4721f391ed90541fddacab5acf947aa0d3dc7d27b2e1e8eda2be8970586c3274", size = 11050, upload-time = "2024-12-04T17:35:26.475Z" },
+]
+
 [[package]]
 name = "sniffio"
 version = "1.3.1"
@@ -1849,6 +1918,51 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/e3/bd/fa9bb053192491b3867ba07d2343d9f2252e00811567d30ae8d0f78136fe/watchfiles-1.1.1-cp314-cp314t-musllinux_1_1_x86_64.whl", hash = "sha256:a916a2932da8f8ab582f242c065f5c81bed3462849ca79ee357dd9551b0e9b01", size = 622112, upload-time = "2025-10-14T15:05:50.941Z" },
 ]

+[[package]]
+name = "websockets"
+version = "16.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/04/24/4b2031d72e840ce4c1ccb255f693b15c334757fc50023e4db9537080b8c4/websockets-16.0.tar.gz", hash = "sha256:5f6261a5e56e8d5c42a4497b364ea24d94d9563e8fbd44e78ac40879c60179b5", size = 179346, upload-time = "2026-01-10T09:23:47.181Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/84/7b/bac442e6b96c9d25092695578dda82403c77936104b5682307bd4deb1ad4/websockets-16.0-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:71c989cbf3254fbd5e84d3bff31e4da39c43f884e64f2551d14bb3c186230f00", size = 177365, upload-time = "2026-01-10T09:22:46.787Z" },
+    { url = "https://files.pythonhosted.org/packages/b0/fe/136ccece61bd690d9c1f715baaeefd953bb2360134de73519d5df19d29ca/websockets-16.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:8b6e209ffee39ff1b6d0fa7bfef6de950c60dfb91b8fcead17da4ee539121a79", size = 175038, upload-time = "2026-01-10T09:22:47.999Z" },
+    { url = "https://files.pythonhosted.org/packages/40/1e/9771421ac2286eaab95b8575b0cb701ae3663abf8b5e1f64f1fd90d0a673/websockets-16.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:86890e837d61574c92a97496d590968b23c2ef0aeb8a9bc9421d174cd378ae39", size = 175328, upload-time = "2026-01-10T09:22:49.809Z" },
+    { url = "https://files.pythonhosted.org/packages/18/29/71729b4671f21e1eaa5d6573031ab810ad2936c8175f03f97f3ff164c802/websockets-16.0-cp312-cp312-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:9b5aca38b67492ef518a8ab76851862488a478602229112c4b0d58d63a7a4d5c", size = 184915, upload-time = "2026-01-10T09:22:51.071Z" },
+    { url = "https://files.pythonhosted.org/packages/97/bb/21c36b7dbbafc85d2d480cd65df02a1dc93bf76d97147605a8e27ff9409d/websockets-16.0-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:e0334872c0a37b606418ac52f6ab9cfd17317ac26365f7f65e203e2d0d0d359f", size = 186152, upload-time = "2026-01-10T09:22:52.224Z" },
+    { url = "https://files.pythonhosted.org/packages/4a/34/9bf8df0c0cf88fa7bfe36678dc7b02970c9a7d5e065a3099292db87b1be2/websockets-16.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:a0b31e0b424cc6b5a04b8838bbaec1688834b2383256688cf47eb97412531da1", size = 185583, upload-time = "2026-01-10T09:22:53.443Z" },
+    { url = "https://files.pythonhosted.org/packages/47/88/4dd516068e1a3d6ab3c7c183288404cd424a9a02d585efbac226cb61ff2d/websockets-16.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:485c49116d0af10ac698623c513c1cc01c9446c058a4e61e3bf6c19dff7335a2", size = 184880, upload-time = "2026-01-10T09:22:55.033Z" },
+    { url = "https://files.pythonhosted.org/packages/91/d6/7d4553ad4bf1c0421e1ebd4b18de5d9098383b5caa1d937b63df8d04b565/websockets-16.0-cp312-cp312-win32.whl", hash = "sha256:eaded469f5e5b7294e2bdca0ab06becb6756ea86894a47806456089298813c89", size = 178261, upload-time = "2026-01-10T09:22:56.251Z" },
+    { url = "https://files.pythonhosted.org/packages/c3/f0/f3a17365441ed1c27f850a80b2bc680a0fa9505d733fe152fdf5e98c1c0b/websockets-16.0-cp312-cp312-win_amd64.whl", hash = "sha256:5569417dc80977fc8c2d43a86f78e0a5a22fee17565d78621b6bb264a115d4ea", size = 178693, upload-time = "2026-01-10T09:22:57.478Z" },
+    { url = "https://files.pythonhosted.org/packages/cc/9c/baa8456050d1c1b08dd0ec7346026668cbc6f145ab4e314d707bb845bf0d/websockets-16.0-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:878b336ac47938b474c8f982ac2f7266a540adc3fa4ad74ae96fea9823a02cc9", size = 177364, upload-time = "2026-01-10T09:22:59.333Z" },
+    { url = "https://files.pythonhosted.org/packages/7e/0c/8811fc53e9bcff68fe7de2bcbe75116a8d959ac699a3200f4847a8925210/websockets-16.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:52a0fec0e6c8d9a784c2c78276a48a2bdf099e4ccc2a4cad53b27718dbfd0230", size = 175039, upload-time = "2026-01-10T09:23:01.171Z" },
+    { url = "https://files.pythonhosted.org/packages/aa/82/39a5f910cb99ec0b59e482971238c845af9220d3ab9fa76dd9162cda9d62/websockets-16.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:e6578ed5b6981005df1860a56e3617f14a6c307e6a71b4fff8c48fdc50f3ed2c", size = 175323, upload-time = "2026-01-10T09:23:02.341Z" },
+    { url = "https://files.pythonhosted.org/packages/bd/28/0a25ee5342eb5d5f297d992a77e56892ecb65e7854c7898fb7d35e9b33bd/websockets-16.0-cp313-cp313-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:95724e638f0f9c350bb1c2b0a7ad0e83d9cc0c9259f3ea94e40d7b02a2179ae5", size = 184975, upload-time = "2026-01-10T09:23:03.756Z" },
+    { url = "https://files.pythonhosted.org/packages/f9/66/27ea52741752f5107c2e41fda05e8395a682a1e11c4e592a809a90c6a506/websockets-16.0-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:c0204dc62a89dc9d50d682412c10b3542d748260d743500a85c13cd1ee4bde82", size = 186203, upload-time = "2026-01-10T09:23:05.01Z" },
+    { url = "https://files.pythonhosted.org/packages/37/e5/8e32857371406a757816a2b471939d51c463509be73fa538216ea52b792a/websockets-16.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:52ac480f44d32970d66763115edea932f1c5b1312de36df06d6b219f6741eed8", size = 185653, upload-time = "2026-01-10T09:23:06.301Z" },
+    { url = "https://files.pythonhosted.org/packages/9b/67/f926bac29882894669368dc73f4da900fcdf47955d0a0185d60103df5737/websockets-16.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:6e5a82b677f8f6f59e8dfc34ec06ca6b5b48bc4fcda346acd093694cc2c24d8f", size = 184920, upload-time = "2026-01-10T09:23:07.492Z" },
+    { url = "https://files.pythonhosted.org/packages/3c/a1/3d6ccdcd125b0a42a311bcd15a7f705d688f73b2a22d8cf1c0875d35d34a/websockets-16.0-cp313-cp313-win32.whl", hash = "sha256:abf050a199613f64c886ea10f38b47770a65154dc37181bfaff70c160f45315a", size = 178255, upload-time = "2026-01-10T09:23:09.245Z" },
+    { url = "https://files.pythonhosted.org/packages/6b/ae/90366304d7c2ce80f9b826096a9e9048b4bb760e44d3b873bb272cba696b/websockets-16.0-cp313-cp313-win_amd64.whl", hash = "sha256:3425ac5cf448801335d6fdc7ae1eb22072055417a96cc6b31b3861f455fbc156", size = 178689, upload-time = "2026-01-10T09:23:10.483Z" },
+    { url = "https://files.pythonhosted.org/packages/f3/1d/e88022630271f5bd349ed82417136281931e558d628dd52c4d8621b4a0b2/websockets-16.0-cp314-cp314-macosx_10_15_universal2.whl", hash = "sha256:8cc451a50f2aee53042ac52d2d053d08bf89bcb31ae799cb4487587661c038a0", size = 177406, upload-time = "2026-01-10T09:23:12.178Z" },
+    { url = "https://files.pythonhosted.org/packages/f2/78/e63be1bf0724eeb4616efb1ae1c9044f7c3953b7957799abb5915bffd38e/websockets-16.0-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:daa3b6ff70a9241cf6c7fc9e949d41232d9d7d26fd3522b1ad2b4d62487e9904", size = 175085, upload-time = "2026-01-10T09:23:13.511Z" },
+    { url = "https://files.pythonhosted.org/packages/bb/f4/d3c9220d818ee955ae390cf319a7c7a467beceb24f05ee7aaaa2414345ba/websockets-16.0-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:fd3cb4adb94a2a6e2b7c0d8d05cb94e6f1c81a0cf9dc2694fb65c7e8d94c42e4", size = 175328, upload-time = "2026-01-10T09:23:14.727Z" },
+    { url = "https://files.pythonhosted.org/packages/63/bc/d3e208028de777087e6fb2b122051a6ff7bbcca0d6df9d9c2bf1dd869ae9/websockets-16.0-cp314-cp314-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:781caf5e8eee67f663126490c2f96f40906594cb86b408a703630f95550a8c3e", size = 185044, upload-time = "2026-01-10T09:23:15.939Z" },
+    { url = "https://files.pythonhosted.org/packages/ad/6e/9a0927ac24bd33a0a9af834d89e0abc7cfd8e13bed17a86407a66773cc0e/websockets-16.0-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:caab51a72c51973ca21fa8a18bd8165e1a0183f1ac7066a182ff27107b71e1a4", size = 186279, upload-time = "2026-01-10T09:23:17.148Z" },
+    { url = "https://files.pythonhosted.org/packages/b9/ca/bf1c68440d7a868180e11be653c85959502efd3a709323230314fda6e0b3/websockets-16.0-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:19c4dc84098e523fd63711e563077d39e90ec6702aff4b5d9e344a60cb3c0cb1", size = 185711, upload-time = "2026-01-10T09:23:18.372Z" },
+    { url = "https://files.pythonhosted.org/packages/c4/f8/fdc34643a989561f217bb477cbc47a3a07212cbda91c0e4389c43c296ebf/websockets-16.0-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:a5e18a238a2b2249c9a9235466b90e96ae4795672598a58772dd806edc7ac6d3", size = 184982, upload-time = "2026-01-10T09:23:19.652Z" },
+    { url = "https://files.pythonhosted.org/packages/dd/d1/574fa27e233764dbac9c52730d63fcf2823b16f0856b3329fc6268d6ae4f/websockets-16.0-cp314-cp314-win32.whl", hash = "sha256:a069d734c4a043182729edd3e9f247c3b2a4035415a9172fd0f1b71658a320a8", size = 177915, upload-time = "2026-01-10T09:23:21.458Z" },
+    { url = "https://files.pythonhosted.org/packages/8a/f1/ae6b937bf3126b5134ce1f482365fde31a357c784ac51852978768b5eff4/websockets-16.0-cp314-cp314-win_amd64.whl", hash = "sha256:c0ee0e63f23914732c6d7e0cce24915c48f3f1512ec1d079ed01fc629dab269d", size = 178381, upload-time = "2026-01-10T09:23:22.715Z" },
+    { url = "https://files.pythonhosted.org/packages/06/9b/f791d1db48403e1f0a27577a6beb37afae94254a8c6f08be4a23e4930bc0/websockets-16.0-cp314-cp314t-macosx_10_15_universal2.whl", hash = "sha256:a35539cacc3febb22b8f4d4a99cc79b104226a756aa7400adc722e83b0d03244", size = 177737, upload-time = "2026-01-10T09:23:24.523Z" },
+    { url = "https://files.pythonhosted.org/packages/bd/40/53ad02341fa33b3ce489023f635367a4ac98b73570102ad2cdd770dacc9a/websockets-16.0-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:b784ca5de850f4ce93ec85d3269d24d4c82f22b7212023c974c401d4980ebc5e", size = 175268, upload-time = "2026-01-10T09:23:25.781Z" },
+    { url = "https://files.pythonhosted.org/packages/74/9b/6158d4e459b984f949dcbbb0c5d270154c7618e11c01029b9bbd1bb4c4f9/websockets-16.0-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:569d01a4e7fba956c5ae4fc988f0d4e187900f5497ce46339c996dbf24f17641", size = 175486, upload-time = "2026-01-10T09:23:27.033Z" },
+    { url = "https://files.pythonhosted.org/packages/e5/2d/7583b30208b639c8090206f95073646c2c9ffd66f44df967981a64f849ad/websockets-16.0-cp314-cp314t-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:50f23cdd8343b984957e4077839841146f67a3d31ab0d00e6b824e74c5b2f6e8", size = 185331, upload-time = "2026-01-10T09:23:28.259Z" },
+    { url = "https://files.pythonhosted.org/packages/45/b0/cce3784eb519b7b5ad680d14b9673a31ab8dcb7aad8b64d81709d2430aa8/websockets-16.0-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:152284a83a00c59b759697b7f9e9cddf4e3c7861dd0d964b472b70f78f89e80e", size = 186501, upload-time = "2026-01-10T09:23:29.449Z" },
+    { url = "https://files.pythonhosted.org/packages/19/60/b8ebe4c7e89fb5f6cdf080623c9d92789a53636950f7abacfc33fe2b3135/websockets-16.0-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:bc59589ab64b0022385f429b94697348a6a234e8ce22544e3681b2e9331b5944", size = 186062, upload-time = "2026-01-10T09:23:31.368Z" },
+    { url = "https://files.pythonhosted.org/packages/88/a8/a080593f89b0138b6cba1b28f8df5673b5506f72879322288b031337c0b8/websockets-16.0-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:32da954ffa2814258030e5a57bc73a3635463238e797c7375dc8091327434206", size = 185356, upload-time = "2026-01-10T09:23:32.627Z" },
+    { url = "https://files.pythonhosted.org/packages/c2/b6/b9afed2afadddaf5ebb2afa801abf4b0868f42f8539bfe4b071b5266c9fe/websockets-16.0-cp314-cp314t-win32.whl", hash = "sha256:5a4b4cc550cb665dd8a47f868c8d04c8230f857363ad3c9caf7a0c3bf8c61ca6", size = 178085, upload-time = "2026-01-10T09:23:33.816Z" },
+    { url = "https://files.pythonhosted.org/packages/9f/3e/28135a24e384493fa804216b79a6a6759a38cc4ff59118787b9fb693df93/websockets-16.0-cp314-cp314t-win_amd64.whl", hash = "sha256:b14dc141ed6d2dde437cddb216004bcac6a1df0935d79656387bd41632ba0bbd", size = 178531, upload-time = "2026-01-10T09:23:35.016Z" },
+    { url = "https://files.pythonhosted.org/packages/6f/28/258ebab549c2bf3e64d2b0217b973467394a9cea8c42f70418ca2c5d0d2e/websockets-16.0-py3-none-any.whl", hash = "sha256:1637db62fad1dc833276dded54215f2c7fa46912301a24bd94d45d46a011ceec", size = 171598, upload-time = "2026-01-10T09:23:45.395Z" },
+]
+
 [[package]]
 name = "yarl"
 version = "1.23.0"
@@ -0,0 +1,327 @@
+"""LiveKit STT plugin for Voxtral Realtime served via vLLM (/v1/realtime).
+
+vLLM exposes Voxtral Realtime over a WebSocket that follows the OpenAI Realtime
+API protocol (not Mistral's proprietary realtime protocol).
+"""
+
+import asyncio
+import base64
+import json
+import logging
+import os
+import weakref
+from collections import deque
+from dataclasses import dataclass
+
+import websockets
+from livekit.agents import (
+    DEFAULT_API_CONNECT_OPTIONS,
+    APIConnectionError,
+    APIConnectOptions,
+    APIStatusError,
+    stt,
+    utils,
+)
+from livekit.agents import (
+    vad as vad_module,
+)
+from livekit.agents.types import NOT_GIVEN, NotGivenOr
+from livekit.agents.utils import is_given
+
+logger = logging.getLogger("voxtral-vllm-stt")
+
+SAMPLE_RATE = 16000
+NUM_CHANNELS = 1
+CHUNK_SAMPLES = 1600  # 100 ms @ 16 kHz mono
+PREROLL_CHUNKS = 5  # keep 500 ms of audio before START_OF_SPEECH
+
+
+@dataclass
+class _STTOptions:
+    base_url: str
+    model: str
+    api_key: str | None
+
+
+class STT(stt.STT):
+    """LiveKit STT speaking the OpenAI Realtime protocol served by vLLM."""
+
+    def __init__(
+        self,
+        *,
+        base_url: NotGivenOr[str] = NOT_GIVEN,
+        model: NotGivenOr[str] = NOT_GIVEN,
+        api_key: NotGivenOr[str] = NOT_GIVEN,
+        vad: vad_module.VAD | None = None,
+    ) -> None:
+        """Build the STT.
+
+        Args:
+            base_url: WebSocket URL of the vLLM realtime endpoint, e.g.
+                ws://example:8000/v1/realtime. Falls back to $VOXTRAL_VLLM_BASE_URL.
+            model: Model name exposed by vLLM, default
+                mistralai/Voxtral-Mini-4B-Realtime-2602.
+            api_key: Optional bearer token. Falls back to $VOXTRAL_VLLM_API_KEY.
+            vad: Voice Activity Detector. If omitted, Silero VAD is loaded.
+        """
+        super().__init__(
+            capabilities=stt.STTCapabilities(streaming=True, interim_results=True)
+        )
+
+        resolved_url = (
+            base_url
+            if is_given(base_url)
+            else os.environ.get(
+                "VOXTRAL_VLLM_BASE_URL", "ws://127.0.0.1:8000/v1/realtime"
+            )
+        )
+        resolved_model = (
+            model
+            if is_given(model)
+            else os.environ.get(
+                "VOXTRAL_VLLM_MODEL", "mistralai/Voxtral-Mini-4B-Realtime-2602"
+            )
+        )
+        resolved_key = (
+            api_key if is_given(api_key) else os.environ.get("VOXTRAL_VLLM_API_KEY")
+        )
+
+        if vad is None:
+            try:
+                from livekit.plugins.silero import VAD as SileroVAD  # noqa: PLC0415
+            except ImportError as exc:
+                raise ImportError(
+                    "livekit-plugins-silero is required for vLLM Voxtral realtime "
+                    "(no server-side endpointing)."
+                ) from exc
+            vad = SileroVAD.load()
+        self._vad = vad
+
+        self._opts = _STTOptions(
+            base_url=resolved_url, model=resolved_model, api_key=resolved_key
+        )
+        self._streams: weakref.WeakSet[SpeechStream] = weakref.WeakSet()
+
+    @property
+    def model(self) -> str:
+        """Return the configured vLLM model name."""
+        return self._opts.model
+
+    @property
+    def provider(self) -> str:
+        """Return the provider identifier."""
+        return "vllm-voxtral-realtime"
+
+    async def _recognize_impl(self, *_args, **_kwargs) -> stt.SpeechEvent:
+        raise NotImplementedError(
+            "vLLM Voxtral Realtime STT only supports streaming recognition."
+        )
+
+    def stream(
+        self,
+        *,
+        conn_options: APIConnectOptions = DEFAULT_API_CONNECT_OPTIONS,
+    ) -> SpeechStream:
+        """Open a new streaming recognition stream."""
+        s = SpeechStream(
+            stt=self,
+            opts=self._opts,
+            vad_instance=self._vad,
+            conn_options=conn_options,
+        )
+        self._streams.add(s)
+        return s
+
+
+class SpeechStream(stt.RecognizeStream):
+    def __init__(
+        self,
+        *,
+        stt: STT,
+        opts: _STTOptions,
+        vad_instance: vad_module.VAD,
+        conn_options: APIConnectOptions,
+    ) -> None:
+        """Init the speech stream."""
+        super().__init__(stt=stt, conn_options=conn_options, sample_rate=SAMPLE_RATE)
+        self._opts = opts
+        self._vad = vad_instance
+        self._utterance_q: asyncio.Queue[bytes | None] | None = None
+        self._speaking = False
+        self._preroll: deque[bytes] = deque(maxlen=PREROLL_CHUNKS)
+        self._inflight: set[asyncio.Task] = set()
+
+    @utils.log_exceptions(logger=logger)
+    async def _run(self) -> None:
+        vad_stream = self._vad.stream()
+
+        bstream = utils.audio.AudioByteStream(
+            sample_rate=SAMPLE_RATE,
+            num_channels=NUM_CHANNELS,
+            samples_per_channel=CHUNK_SAMPLES,
+        )
+
+        async def input_task() -> None:
+            async for data in self._input_ch:
+                if isinstance(data, self._FlushSentinel):
+                    for frame in bstream.flush():
+                        self._handle_chunk(frame.data.tobytes())
+                    continue
+
+                vad_stream.push_frame(data)
+                for frame in bstream.write(data.data.tobytes()):
+                    self._handle_chunk(frame.data.tobytes())
+
+            vad_stream.end_input()
+
+        async def vad_task() -> None:
+            async for ev in vad_stream:
+                if ev.type == vad_module.VADEventType.START_OF_SPEECH:
+                    self._on_start_of_speech()
+                elif ev.type == vad_module.VADEventType.END_OF_SPEECH:
+                    self._on_end_of_speech()
+
+        try:
+            await asyncio.gather(input_task(), vad_task())
+            if self._inflight:
+                await asyncio.gather(*self._inflight, return_exceptions=True)
+        finally:
+            for task in self._inflight:
+                if not task.done():
+                    task.cancel()
+            await vad_stream.aclose()
+
+    def _handle_chunk(self, chunk: bytes) -> None:
+        self._preroll.append(chunk)
+        if self._speaking and self._utterance_q is not None:
+            self._utterance_q.put_nowait(chunk)
+
+    def _on_start_of_speech(self) -> None:
+        if self._speaking:
+            return
+        self._speaking = True
+        q: asyncio.Queue[bytes | None] = asyncio.Queue()
+        for chunk in self._preroll:
+            q.put_nowait(chunk)
+        self._utterance_q = q
+        self._event_ch.send_nowait(
+            stt.SpeechEvent(type=stt.SpeechEventType.START_OF_SPEECH)
+        )
+        task = asyncio.create_task(self._run_utterance(q))
+        self._inflight.add(task)
+        task.add_done_callback(self._inflight.discard)
+
+    def _on_end_of_speech(self) -> None:
+        if not self._speaking:
+            return
+        self._speaking = False
+        if self._utterance_q is not None:
+            self._utterance_q.put_nowait(None)
+        self._utterance_q = None
+        self._event_ch.send_nowait(
+            stt.SpeechEvent(type=stt.SpeechEventType.END_OF_SPEECH)
+        )
+
+    async def _run_utterance(self, q: asyncio.Queue[bytes | None]) -> None:
+        headers: dict[str, str] = {}
+        if self._opts.api_key:
+            headers["Authorization"] = f"Bearer {self._opts.api_key}"
+
+        try:
+            async with websockets.connect(
+                self._opts.base_url,
+                additional_headers=headers,
+                open_timeout=self._conn_options.timeout,
+            ) as ws:
+                request_id = await self._handshake(ws)
+
+                send_t = asyncio.create_task(self._send_audio(ws, q))
+                try:
+                    await self._receive_events(ws, request_id)
+                finally:
+                    if not send_t.done():
+                        send_t.cancel()
+                    try:
+                        await send_t
+                    except asyncio.CancelledError:
+                        pass
+                    except Exception:
+                        logger.exception("send-audio task failed during finalize")
+        except (APIStatusError, APIConnectionError, asyncio.CancelledError):
+            raise
+        except Exception as exc:
+            logger.exception("vLLM realtime utterance failed")
+            raise APIConnectionError() from exc
+
+    async def _handshake(self, ws: websockets.ClientConnection) -> str:
+        created = json.loads(await ws.recv())
+        if created.get("type") != "session.created":
+            raise APIStatusError(
+                f"expected session.created, got {created}",
+                status_code=500,
+                body=created,
+            )
+        await ws.send(json.dumps({"type": "session.update", "model": self._opts.model}))
+        await ws.send(json.dumps({"type": "input_audio_buffer.commit"}))
+        return created.get("id", "")
+
+    @staticmethod
+    async def _send_audio(
+        ws: websockets.ClientConnection, q: asyncio.Queue[bytes | None]
+    ) -> None:
+        while True:
+            chunk = await q.get()
+            if chunk is None:
+                await ws.send(
+                    json.dumps({"type": "input_audio_buffer.commit", "final": True})
+                )
+                return
+            await ws.send(
+                json.dumps(
+                    {
+                        "type": "input_audio_buffer.append",
+                        "audio": base64.b64encode(chunk).decode("ascii"),
+                    }
+                )
+            )
+
+    async def _receive_events(
+        self, ws: websockets.ClientConnection, request_id: str
+    ) -> None:
+        current_text = ""
+        async for raw in ws:
+            data = json.loads(raw)
+            event_type = data.get("type")
+
+            if event_type == "transcription.delta":
+                # TODO: fix this
+                current_text += data.get("delta", "")
+            elif event_type == "transcription.done":
+                final_text = data.get("text") or current_text
+                self._event_ch.send_nowait(
+                    stt.SpeechEvent(
+                        type=stt.SpeechEventType.FINAL_TRANSCRIPT,
+                        request_id=request_id,
+                        alternatives=[stt.SpeechData(text=final_text, language="")],
+                    )
+                )
+                usage = data.get("usage") or {}
+                self._event_ch.send_nowait(
+                    stt.SpeechEvent(
+                        type=stt.SpeechEventType.RECOGNITION_USAGE,
+                        request_id=request_id,
+                        recognition_usage=stt.RecognitionUsage(
+                            audio_duration=float(
+                                usage.get("audio_seconds")
+                                or usage.get("prompt_audio_seconds")
+                                or 0
+                            ),
+                            input_tokens=int(usage.get("prompt_tokens") or 0),
+                            output_tokens=int(usage.get("completion_tokens") or 0),
+                        ),
+                    )
+                )
+                return
+            elif event_type == "error":
+                err = data.get("error")
+                raise APIStatusError(str(err), status_code=500, body=data)
@@ -65,7 +65,7 @@ def get_frontend_configuration(request):
            else None,
            "default_country": settings.ROOM_TELEPHONY_DEFAULT_COUNTRY,
        },
-        "subtitle": {"enabled": settings.ROOM_SUBTITLE_ENABLED},
+        "subtitle": {"enabled": True},  # settings.ROOM_SUBTITLE_ENABLED},
        "livekit": {
            "url": settings.LIVEKIT_CONFIGURATION["url"],
            "force_wss_protocol": settings.LIVEKIT_FORCE_WSS_PROTOCOL,
@@ -586,8 +586,7 @@ class RoomViewSet(
            permissions.HasLiveKitRoomAccess,
        ],
        authentication_classes=[LiveKitTokenAuthentication],
-    )
-    @FeatureFlag.require("subtitle")
+    )  # @FeatureFlag.require("subtitle")
    def start_subtitle(self, request, pk=None):  # pylint: disable=unused-argument
        """Start realtime transcription for the room.

@@ -47,6 +47,8 @@ export class RnnNoiseProcessor implements AudioProcessorInterface {
    )

    this.destinationNode = audioContext.createMediaStreamDestination()
+    // this.destinationNode.channelCount = 1
+    // this.destinationNode.channelCountMode = 'explicit'

    // Connect the audio processing chain
    this.sourceNode