Studio/opencode
5
0
Fork 0
mirror of https://gitee.com/zhangsken/opencode.git synced 2026-10-16 10:30:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix(ai): enable AssemblyAI speaker labels when speakers is set (#51369)

Browse Source
This commit is contained in:
Shoubhit Dash
2026-09-25 22:11:44 +05:30
committed by GitHub
parent 4eb46a8885
commit 65d5123ead
2 changed files with 26 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/ai/src/protocols/assemblyai-transcription.ts
+5 -2
View File
@@ -110,8 +110,11 @@ const fromRequest = Effect.fn("AssemblyAITranscription.fromRequest")(function* (
language_code: request.language,
language_detection: request.language === undefined ? true : undefined,
prompt: request.prompt,
// Turn-level `utterances`, the only segments AssemblyAI returns, require speaker labels.
speaker_labels: request.diarize === true || request.timestamps === "segment" ? true : undefined,
// Turn-level `utterances`, the only segments AssemblyAI returns, and `speakers_expected` require speaker labels.
speaker_labels:
request.diarize === true || request.timestamps === "segment" || request.speakers !== undefined
? true
: undefined,
speakers_expected: request.speakers,
},
request.providerOptions,
packages/ai/test/transcription.test.ts
+21 -1
View File
@@ -5,7 +5,7 @@ import { HttpClientRequest } from "effect/unstable/http"
import { Media, Transcription, TranscriptionClient } from "../src/index.js"
import { AssemblyAI, Deepgram, Google, OpenAI } from "../src/providers.js"
import { it } from "./lib/effect.js"
import { dynamicResponse } from "./lib/http.js"
import { dynamicResponse, json, observe, type Call } from "./lib/http.js"
const layer = (handler: Parameters<typeof dynamicResponse>[0]) =>
TranscriptionClient.layer.pipe(Layer.provideMerge(dynamicResponse(handler)))
@@ -171,4 +171,24 @@ describe("Transcription", () => {
expect(failure.reason).toMatchObject({ _tag: "ProviderInternal", body: failed })
}),
)
it.effect("enables AssemblyAI speaker labels when only an expected speaker count is given", () =>
Effect.gen(function* () {
const calls: Array<Call> = []
yield* Transcription.start({ model: assemblyai, audio: Media.url("https://a.test/call.mp3"), speakers: 2 }).pipe(
Effect.provide(
layer((input) => observe(calls, input).pipe(Effect.as(json(input, { id: "tr_1", status: "queued" })))),
),
)
expect(calls.map((call) => JSON.parse(call.body))).toEqual([
{
audio_url: "https://a.test/call.mp3",
speech_models: ["universal-3-5-pro"],
language_detection: true,
speaker_labels: true,
speakers_expected: 2,
},
])
}),
)
})