@opencode/ai 0.0.0-dev-20206 → 0.0.0-dev-20208

package/dist/protocols/deepgram-speech.js

@@ -50,23 +50,25 @@ const fromRequest = Effect.fn("DeepgramSpeech.fromRequest")(function* (request)
 // ---------------------------------------------------------------------------
 // 6. Stream parsing
 // ---------------------------------------------------------------------------
+/** Deepgram wraps raw encodings in WAV unless `container` is `none`, and defaults their sample rate per encoding. */
 const HEADERLESS_ENCODINGS = {
-    linear16: "pcm_s16le",
-    mulaw: "pcm_mulaw",
-    alaw: "pcm_alaw",
+    linear16: { encoding: "pcm_s16le", sampleRate: 24000 },
+    mulaw: { encoding: "pcm_mulaw", sampleRate: 8000 },
+    alaw: { encoding: "pcm_alaw", sampleRate: 8000 },
 };
 const finish = (state, context) => {
     const headers = context.http.headers;
     const mediaType = headers["content-type"];
     const format = audioFormat(context.request);
-    const encoding = HEADERLESS_ENCODINGS[format.encoding ?? ""];
+    const headerless = HEADERLESS_ENCODINGS[format.encoding ?? ""];
+    const container = format.container ?? (headerless === undefined ? undefined : "wav");
     const requestID = headers["dg-request-id"];
     const modelName = headers["dg-model-name"];
     return SpeechStream.finish(route, state, {
-        ...(format.container === "none" && encoding !== undefined
-            ? SpeechStream.pcm(encoding, SpeechStream.sampleRate(mediaType), mediaType)
+        ...(container === "none" && headerless !== undefined
+            ? SpeechStream.pcm(headerless.encoding, SpeechStream.sampleRate(mediaType) ?? context.request.providerOptions?.sampleRate ?? headerless.sampleRate, mediaType)
             : // Deepgram's default encoding is MP3; WAV is a container around any encoding.
-                { mediaType, info: { format: format.container === "wav" ? "wav" : (format.encoding ?? "mp3") } }),
+                { mediaType, info: { format: container === "wav" ? "wav" : (format.encoding ?? "mp3") } }),
         usage: SpeechStream.headerUsage("characters", headers["dg-char-count"]),
         providerMetadata: requestID === undefined && modelName === undefined
             ? undefined

package/dist/protocols/openai-speech.js

@@ -30,10 +30,13 @@ const decodeEvent = route.decodeFrame(SpeechStreamEvent);
 // ---------------------------------------------------------------------------
 // `sse` is not supported for `tts-1` or `tts-1-hd`; those models stream the raw audio body instead.
 const supportsSse = (model) => !/^tts-1(-hd)?(-|$)/.test(model);
+const FORMATS = new Set(["mp3", "opus", "aac", "flac", "wav", "pcm"]);
 const fromRequest = Effect.fn("OpenAISpeech.fromRequest")(function* (request) {
     // Not in `unsupported`: that list would also reject `timestamps: false`, which asks for nothing.
     if (request.timestamps === true)
         return yield* route.unsupported("media.timestamps", `${route.name} does not return timestamps`);
+    if (request.format !== undefined && !FORMATS.has(request.format))
+        return yield* route.unsupported("media.format", `${route.name} supports the mp3, opus, aac, flac, wav, and pcm formats, not "${request.format}"`);
     return MediaProtocol.json(mergeJsonRecords({
         model: request.model.id,
         input: request.text,
@@ -73,7 +76,9 @@ const onEvent = Effect.fn("OpenAISpeech.onEvent")(function* (state, frame) {
 const finish = (state, context) => {
     if (isSse(context.body) && !state.done)
         return Effect.fail(route.incomplete());
-    const format = context.request.format ?? "mp3";
+    // The sent body reflects `providerOptions` and `http.body` overrides of `format`.
+    const sent = context.body.type === "json" ? context.body.value.response_format : undefined;
+    const format = typeof sent === "string" ? sent : "mp3";
     return SpeechStream.finish(route, state, {
         ...(format === "pcm" ? SpeechStream.pcm("pcm_s16le", PCM_SAMPLE_RATE) : SpeechStream.container(format)),
         usage: state.usage,

package/package.json

@@ -1,6 +1,6 @@
 {
   "$schema": "https://json.schemastore.org/package.json",
-  "version": "0.0.0-dev-20206",
+  "version": "0.0.0-dev-20208",
   "name": "@opencode/ai",
   "type": "module",
   "license": "MIT",
@@ -34,7 +34,7 @@
   "devDependencies": {
     "@clack/prompts": "1.0.0-alpha.1",
     "@effect/platform-node": "4.0.0-rc.112",
-    "@opencode/http-recorder": "0.0.0-dev-20206",
+    "@opencode/http-recorder": "0.0.0-dev-20208",
     "@tsconfig/bun": "1.0.9",
     "@types/bun": "1.4.0",
     "@typescript/native-preview": "7.0.0-dev.20251207.1",
@@ -44,7 +44,7 @@
     "@aws-sdk/credential-providers": "3.1057.0",
     "@smithy/eventstream-codec": "4.2.14",
     "@smithy/util-utf8": "4.2.2",
-    "@opencode/schema": "0.0.0-dev-20206",
+    "@opencode/schema": "0.0.0-dev-20208",
     "aws4fetch": "1.0.20",
     "effect": "4.0.0-rc.112",
     "google-auth-library": "10.5.0"