feat(providers): self-hosted OpenAI-compatible STT, TTS and embedding providers

Add Self-hosted STT/TTS/Embedding providers that read baseUrl per connection
instead of a fixed registry endpoint, so 9Router can point at whisper.cpp,
faster-whisper, Kokoro-FastAPI, llama-server, vLLM, Infinity, and similar
OpenAI-compatible local servers.

Self-hosted Embedding refuses to run without a baseUrl rather than falling
back to api.openai.com like openaiCompatNode does, since that fallback would
silently send input text and the API key to OpenAI under a provider named
"Self-hosted". Also fixes embeddingsCore to catch adapter build errors as a
400 instead of letting them escape uncaught, and bounds the upstream fetch
with FETCH_CONNECT_TIMEOUT_MS to avoid hanging forever on a dead endpoint.

Self-hosted TTS treats a bare model value as the model rather than the voice,
since the generic OpenAI TTS convention (bare = voice) is backwards for a
provider where the model is the variable part.

open-sse/providers/registry/index.js

@@ -117,6 +117,9 @@ import p113 from "./morph.js";
 // import p104 from "./windsurf.js";
 import p115 from "./poolside.js";
 import p116 from "./tokenrouter.js";
+import p117 from "./selfhosted-stt.js";
+import p118 from "./selfhosted-tts.js";
+import p119 from "./selfhosted-embedding.js";
 
 export default [
   p0,
@@ -235,4 +238,7 @@ export default [
   // p104, // windsurf — hidden, no tool calling
   p115,
   p116,
+  p117,
+  p118,
+  p119,
 ];

open-sse/providers/registry/selfhosted-embedding.js

@@ -0,0 +1,73 @@
+// Self-hosted, OpenAI-compatible embeddings (llama.cpp / llama-server, vLLM,
+// Infinity, text-embeddings-inference, ...) — the embeddings counterpart of
+// selfhosted-stt and selfhosted-tts.
+//
+// Routing a self-hosted embeddings server already WORKS today, via a custom
+// provider node: getEmbeddingAdapter() matches `openai-compatible-*` and
+// `custom-embedding-*` and returns openaiCompatNode, whose buildUrl reads
+// creds.providerSpecificData.baseUrl. What is missing is a first-class provider,
+// and the gap is visible rather than functional:
+//
+//   /v1/embeddings on such a node          -> 200, correct vectors
+//   the Embedding page in the dashboard    -> the node is not listed at all
+//
+// The page renders getProvidersByKind("embedding") plus provider nodes filtered
+// to `type === "custom-embedding"`. A node created as `openai-compatible` — the
+// natural choice when ONE endpoint serves chat and embeddings behind the same
+// front door — satisfies neither, so a working self-hosted embeddings endpoint is
+// invisible on the page whose job is to show embeddings providers. Diagnosed on a
+// deployment serving Qwen3-Embedding-8B at 4096 dimensions through exactly that
+// shape (2026-08-04).
+//
+// Declaring it as a provider with serviceKinds: ["embedding"] puts it on the page
+// beside Voyage, Jina and the rest, and keeps the per-connection baseUrl that
+// makes self-hosting possible at all.
+//
+// authType is "apikey" rather than "none" for the same reason as the STT and TTS
+// entries: it is what gives the connection a credentials record, and
+// providerSpecificData.baseUrl lives there. Local servers ignore the key itself;
+// any non-empty value works.
+export default {
+  id: "selfhosted-embedding",
+  priority: 50,
+  hasFree: true,
+  alias: "selfhosted-embedding",
+  display: {
+    name: "Self-hosted Embedding",
+    icon: "cloud",
+    color: "#ffffffff",
+    textIcon: "SE",
+    website: "https://github.com/ggml-org/llama.cpp",
+  },
+  category: "apikey",
+  auth: {
+    apiKey: {
+      // Note the /v1: the adapter appends "/embeddings" to whatever it is given,
+      // so a bare http://host:8080 resolves to http://host:8080/embeddings and
+      // misses the OpenAI route entirely. Give it the OpenAI base, the same value
+      // an OpenAI client would use. A trailing /embeddings is tolerated.
+      text: "Set providerSpecificData.baseUrl to the OpenAI base URL, e.g. http://host:8080/v1 — /embeddings is appended. The API key is not checked by local servers; any value works.",
+    },
+  },
+  // A self-hosted server serves whatever model it was started with, so the id
+  // here is a placeholder for the UI: the request passes `model` straight
+  // through, and llama-server ignores an unknown value rather than rejecting it.
+  // Dimensions are deliberately NOT declared — they are a property of the loaded
+  // weights, and asserting a number here would be a guess that silently
+  // contradicts the server.
+  models: [
+    { id: "embedding", name: "Self-hosted embedding model", kind: "embedding" },
+  ],
+  serviceKinds: ["embedding"],
+  embeddingConfig: {
+    // Declared for shape-consistency with the other embedding providers, and
+    // read by the UI — but NOT by the request path. openaiCompatNode resolves the
+    // URL purely from creds.providerSpecificData.baseUrl (falling back to
+    // api.openai.com), so unlike a fixed cloud provider this baseUrl never
+    // reaches the wire. Stated plainly because a reader would otherwise
+    // reasonably assume it is the default endpoint.
+    baseUrl: "http://localhost:8080/v1/embeddings",
+    authType: "apikey",
+    authHeader: "bearer",
+  },
+};

open-sse/providers/registry/selfhosted-stt.js

@@ -0,0 +1,48 @@
+// Self-hosted, OpenAI-compatible speech-to-text (whisper.cpp, faster-whisper,
+// Speaches, vLLM-served Whisper, ...).
+//
+// Every other STT provider here is a named cloud service with a fixed endpoint.
+// This one exists so a locally-served /v1/audio/transcriptions can be used at
+// all: set the connection's providerSpecificData.baseUrl to the full URL of the
+// endpoint, exactly as the custom embedding providers already work.
+//
+// sttCore dispatches on `format`; anything that is not one of the five named
+// cloud shapes falls through to transcribeOpenAICompatible, which POSTs the
+// standard multipart body (file, model, and optional language / prompt /
+// response_format / temperature). That is precisely what whisper.cpp's OpenAI
+// endpoint accepts.
+//
+// authType is "apikey" rather than "none" so the connection carries a
+// credentials record — which is where providerSpecificData.baseUrl lives. Local
+// servers ignore the key itself; any non-empty value works.
+export default {
+  id: "selfhosted-stt",
+  priority: 50,
+  hasFree: true,
+  alias: "selfhosted-stt",
+  display: {
+    name: "Self-hosted STT",
+    icon: "cloud",
+    color: "#ffffffff",
+    textIcon: "ST",
+    website: "https://github.com/ggml-org/whisper.cpp",
+  },
+  category: "apikey",
+  auth: {
+    apiKey: {
+      text: "Set providerSpecificData.baseUrl to the full transcriptions URL, e.g. http://host:8080/v1/audio/transcriptions. The API key is not checked by local servers; any value works.",
+    },
+  },
+  models: [
+    { id: "whisper-1", name: "Whisper (self-hosted)", params: ["language", "response_format", "temperature", "prompt"], kind: "stt" },
+  ],
+  serviceKinds: ["stt"],
+  sttConfig: {
+    // Overridden per connection by providerSpecificData.baseUrl; this default
+    // only makes the provider usable out of the box on a same-host deployment.
+    baseUrl: "http://localhost:8080/v1/audio/transcriptions",
+    authType: "apikey",
+    authHeader: "bearer",
+    format: "openai",
+  },
+};

open-sse/providers/registry/selfhosted-tts.js

@@ -0,0 +1,44 @@
+// Self-hosted, OpenAI-compatible text-to-speech (Kokoro-FastAPI, openedai-speech,
+// vLLM-served TTS, ...) — the TTS counterpart of selfhosted-stt.
+//
+// Every other self-hostable TTS provider here (coqui, tortoise) carries a FIXED
+// localhost baseUrl in its registry entry and `authType: "none"`, and the generic
+// dispatcher reads `ttsConfig.baseUrl` from that entry rather than from the
+// connection. So there was no way to point TTS at a server on another host.
+//
+// `authType: "apikey"` is what makes the override possible at all: it gives the
+// connection a credentials record, which is where providerSpecificData.baseUrl
+// lives. Local servers ignore the key; any non-empty value works.
+export default {
+  id: "selfhosted-tts",
+  priority: 50,
+  hasFree: true,
+  alias: "selfhosted-tts",
+  display: {
+    name: "Self-hosted TTS",
+    icon: "cloud",
+    color: "#ffffffff",
+    textIcon: "TT",
+    website: "https://github.com/remsky/Kokoro-FastAPI",
+  },
+  category: "apikey",
+  auth: {
+    apiKey: {
+      text: "Set providerSpecificData.baseUrl to the server root, e.g. http://host:8080 — /v1/audio/speech is appended. The API key is not checked by local servers; any value works.",
+    },
+  },
+  // Voice is selected as "<model>/<voice>", the same convention the OpenAI TTS
+  // adapter uses, so existing clients need no special casing.
+  models: [
+    { id: "kokoro", name: "Kokoro (self-hosted)", params: ["voice", "response_format", "speed"], kind: "tts" },
+  ],
+  serviceKinds: ["tts"],
+  ttsConfig: {
+    // Overridden per connection by providerSpecificData.baseUrl; this default
+    // only makes the provider usable on a same-host deployment.
+    baseUrl: "http://localhost:8880",
+    defaultModel: "kokoro",
+    authType: "apikey",
+    format: "openai-speech",
+  },
+};