mirror of
https://gitee.com/zhangsken/opencode.git
synced 2026-10-16 10:30:01 +08:00
feat(ai): add ElevenLabs Scribe transcription route (#51641)
This commit is contained in:
Shoubhit Dash
@@ -102,7 +102,7 @@ Media does not fit the SSE-frames-to-event-state-machine LLM route. `MediaRoute.
|
||||
|
||||
`MediaProtocol.stream` is the incremental kind every speech route uses, with the same discipline as LLM protocols. `MediaRoute.stream` submits the caller's request as `MediaProtocol.Addressed<Request>` (`{ ...request, mode }`, `mode: "generate" | "stream"`), so one provider stays one protocol: `body.from`, the endpoint path, and `frames` read `request.mode` to pick the body, path, and framing. `frames(bytes, context)` returns frames — `Framing.sse`, `Framing.lines`, `Framing.document` (a single-document response shaped like a streamed record), or the raw `bytes` for chunked audio. `initial()` is fresh per-response parser state; `step` folds each frame into it and emits modality events; `finish(state, context)` runs once after the last frame with the request, body, and observed `http` (header-only usage lives there) and emits exactly one terminal event or fails with `route.incomplete()`. Keep parser state to real accumulators and derive anything the request or body determines in `finish`. `generate` runs the same stream and folds it with the modality's `collect`. Request-derived URL parameters go on the body's `query` (array values repeat the parameter), applied before route and caller `http.query`. Decode frames with `route.decodeFrame` and raise stream-time failures with `route.frameError` (the frame stays on `reason.body`); protocols never thread HTTP context, because the route fills `reason.http` on stream errors that lack it. Speech protocols share `protocols/utils/speech-stream.ts` for deltas, timestamps, voice ids, PCM and container descriptions, and the terminal asset.
|
||||
|
||||
Every modality route is the inline | stream | queued union (transcription uses all three: OpenAI and Gemini stream, Deepgram is inline, AssemblyAI is queued), every client is `MediaClient.make(Service, { modality, responseEvents })` (`src/media-client.ts`), which dispatches on the route's `kind`, and every model composes through `composeRoute`. fal queue protocols come from `protocols/utils/fal-queue.ts`, bodies are `json`, `multipart`, or `binary` (a raw upload), and a queued protocol that must upload media before submitting implements `start.prepare` (`MediaProtocol.Prepare`; AssemblyAI `/v2/upload`).
|
||||
Every modality route is the inline | stream | queued union (transcription uses all three: OpenAI and Gemini stream, Deepgram and ElevenLabs are inline, AssemblyAI is queued), every client is `MediaClient.make(Service, { modality, responseEvents })` (`src/media-client.ts`), which dispatches on the route's `kind`, and every model composes through `composeRoute`. fal queue protocols come from `protocols/utils/fal-queue.ts`, bodies are `json`, `multipart`, or `binary` (a raw upload), and a queued protocol that must upload media before submitting implements `start.prepare` (`MediaProtocol.Prepare`; AssemblyAI `/v2/upload`).
|
||||
|
||||
### URL Construction
|
||||
|
||||
|
||||
+14
-8
@@ -873,11 +873,12 @@ for await (const event of ai.speech.stream({ model, text: "Hello from OpenCode."
|
||||
## Transcription
|
||||
|
||||
Transcription (speech-to-text) is the one modality whose providers use every route kind: OpenAI and Gemini stream,
|
||||
Deepgram answers inline, and AssemblyAI is queued. `Transcription.generate` and `Transcription.stream` work on all of
|
||||
them; `Transcription.start` / `resume` return a `Generation` on queued routes and fail with `UnsupportedOperation`
|
||||
elsewhere. Models come from `.transcription(...)` selectors on the `OpenAI`, `Google`, `Deepgram`, and `AssemblyAI`
|
||||
facades. Common fields (`language`, `prompt`, `timestamps: "none" | "segment" | "word"`, `diarize`, `speakers`) lower
|
||||
natively or fail with a typed `AIError` before any network call; a route may return more than asked.
|
||||
Deepgram and ElevenLabs answer inline, and AssemblyAI is queued. `Transcription.generate` and `Transcription.stream`
|
||||
work on all of them; `Transcription.start` / `resume` return a `Generation` on queued routes and fail with
|
||||
`UnsupportedOperation` elsewhere. Models come from `.transcription(...)` selectors on the `OpenAI`, `Google`,
|
||||
`Deepgram`, `ElevenLabs`, and `AssemblyAI` facades. Common fields (`language`, `prompt`,
|
||||
`timestamps: "none" | "segment" | "word"`, `diarize`, `speakers`) lower natively or fail with a typed `AIError` before
|
||||
any network call; a route may return more than asked.
|
||||
|
||||
```ts
|
||||
import { Console, Effect, Stream } from "effect"
|
||||
@@ -889,7 +890,7 @@ const openai = OpenAI.configure({ apiKey: process.env.OPENAI_API_KEY })
|
||||
const program = Effect.gen(function* () {
|
||||
const audio = yield* Media.file("./call.mp3")
|
||||
|
||||
// Speaker-labelled segments; labels are provider-native strings ("A", "0", "spk:0").
|
||||
// Speaker-labelled segments; labels are provider-native strings ("A", "0", "spk:0", "speaker_0").
|
||||
const response = yield* Transcription.generate({
|
||||
model: Deepgram.configure({ apiKey }).transcription("nova-3"),
|
||||
audio,
|
||||
@@ -899,7 +900,7 @@ const program = Effect.gen(function* () {
|
||||
response.text // "Hello from OpenCode."
|
||||
response.segments // [{ text, startSeconds, endSeconds, speaker: "0" }]
|
||||
response.words // [{ text, startSeconds, endSeconds, speaker, confidence }]
|
||||
response.language // the provider's own value, lowercased ("en", "english", "en_us")
|
||||
response.language // the provider's own value, lowercased ("en", "eng", "english", "en_us")
|
||||
|
||||
// Text deltas as the model transcribes, then one finish carrying the whole transcript.
|
||||
yield* Transcription.stream({ model: openai.transcription("gpt-4o-mini-transcribe"), audio }).pipe(
|
||||
@@ -923,7 +924,12 @@ Provider notes:
|
||||
- **OpenAI** takes inline audio only; `diarize` needs `gpt-4o-transcribe-diarize`, timestamps need `whisper-1`, and `whisper-1` does not stream.
|
||||
- **Gemini** needs a transcribe model (`gemini-3.5-transcribe`); `prompt` and `speakers` fail typed.
|
||||
- **Deepgram** detects the language unless `language` is set; vocabulary goes in `providerOptions.keyterm`.
|
||||
- **AssemblyAI** uploads inline audio before submitting and is the only route that accepts `speakers`.
|
||||
- **ElevenLabs** (`scribe_v2`) uploads inline audio as the multipart `file` and sends a URL as `source_url`. Words
|
||||
always carry timestamps, and segments are speaker turns, so `diarize`, `timestamps: "segment"`, or `speakers` turns
|
||||
on diarization. `speakers` is an upper bound (`num_speakers`); `prompt` fails typed (vocabulary goes in
|
||||
`providerOptions.keyterms`), as do webhook delivery and per-channel output (`use_multi_channel` without
|
||||
`multichannel_output_style: "combined"`).
|
||||
- **AssemblyAI** uploads inline audio before submitting and treats `speakers` as the exact speaker count.
|
||||
|
||||
The promise client mirrors the Effect API:
|
||||
|
||||
|
||||
@@ -1,7 +1,6 @@
|
||||
# Media generation in `@opencode/ai` — public API direction
|
||||
|
||||
Status: phases 1–4 implemented (through Image queued routes and partial images; ElevenLabs Scribe transcription
|
||||
pending); phase 5 proposal.
|
||||
Status: phases 1–4 implemented (through Image queued routes and partial images); phase 5 proposal.
|
||||
|
||||
## Goal
|
||||
|
||||
@@ -271,8 +270,8 @@ Deferred: `Speech.session(...)` — input-streaming TTS where text arrives incre
|
||||
#### Transcription (STT)
|
||||
|
||||
Shipped as the second half of phase 3 (`src/transcription.ts`, `src/transcription-client.ts`, protocols
|
||||
`openai-transcription`, `google-transcription`, `deepgram-transcription`, `assemblyai-transcription`; new `AssemblyAI`
|
||||
facade).
|
||||
`openai-transcription`, `google-transcription`, `deepgram-transcription`, `elevenlabs-transcription`,
|
||||
`assemblyai-transcription`; new `AssemblyAI` facade).
|
||||
|
||||
```ts
|
||||
const request = Transcription.request({
|
||||
@@ -281,7 +280,7 @@ const request = Transcription.request({
|
||||
language: "en", // provider-native passthrough
|
||||
timestamps: "segment", // none | segment | word
|
||||
diarize: true,
|
||||
speakers: 2, // exact speaker count (AssemblyAI only)
|
||||
speakers: 2, // speaker count (AssemblyAI exact, ElevenLabs maximum)
|
||||
providerOptions: { known_speaker_names: ["agent"] },
|
||||
})
|
||||
|
||||
@@ -309,17 +308,23 @@ upload); `packages/ai/AGENTS.md` (Media Routes) describes both.
|
||||
Settled rules:
|
||||
|
||||
- **Timestamps.** A granularity the selected route or model cannot produce fails as `UnsupportedOperation`
|
||||
(`media.timestamps`), following Speech; a route that returns more than asked (Deepgram and AssemblyAI always return
|
||||
words) is not stripped. Segments always carry start and end times: Gemini times each transcription part from its
|
||||
(`media.timestamps`), following Speech; a route that returns more than asked (Deepgram, ElevenLabs, and AssemblyAI
|
||||
always return words) is not stripped. Segments always carry start and end times: Gemini times each transcription part from its
|
||||
word offsets, so segment timestamps and diarization also request word offsets there.
|
||||
- **Diarization.** `diarize` means segments (and words, where the provider labels them) carry `speaker`. Labels are
|
||||
provider-native strings — OpenAI `A` or a known speaker name, Deepgram `0`, Gemini `spk:0`, AssemblyAI `A` — with no
|
||||
cross-provider speaker model. `speakers` is the exact number of speakers to label, which AssemblyAI (`speakers_expected`, the only route that
|
||||
accepts it) treats as a constraint rather than a hint.
|
||||
provider-native strings — OpenAI `A` or a known speaker name, Deepgram `0`, Gemini `spk:0`, AssemblyAI `A`,
|
||||
ElevenLabs `speaker_0` — with no cross-provider speaker model. `speakers` is the number of speakers to label:
|
||||
AssemblyAI (`speakers_expected`) treats it as an exact constraint rather than a hint, and ElevenLabs
|
||||
(`num_speakers`) as the maximum. Both turn on diarization for it; the other routes reject it.
|
||||
- **Segments from words.** ElevenLabs returns only a token list (`word`, `spacing`, `audio_event`), so its segments
|
||||
are speaker turns: consecutive words and spacing with one `speaker_id`, text joined from the provider's own spacing
|
||||
tokens. `words` drops spacing and audio events. Segments therefore need diarization, which `timestamps: "segment"`
|
||||
turns on, as AssemblyAI's utterances need speaker labels.
|
||||
- **Language** is passed through (`language`, OpenAI `gpt-transcribe` `languages[]`, Gemini `languageCodes`,
|
||||
AssemblyAI `language_code`). `response.language` is the provider's own value, lowercased but not normalized: an
|
||||
ISO code on most routes (AssemblyAI's detection returns `en`), `english` from whisper-1. Deepgram and AssemblyAI
|
||||
assume English unless asked to detect, so a missing `language` enables their detection.
|
||||
AssemblyAI and ElevenLabs `language_code`). `response.language` is the provider's own value, lowercased but not
|
||||
normalized: an ISO code on most routes (AssemblyAI's detection returns `en`, ElevenLabs ISO 639-3 `eng`), `english`
|
||||
from whisper-1. Deepgram and AssemblyAI assume English unless asked to detect, so a missing `language` enables their
|
||||
detection.
|
||||
- **Gemini** requires a transcribe model; other model ids fail with `UnsupportedOperation` before the call, because
|
||||
general models ignore `audioTranscriptionConfig` and answer conversationally. Streamed chunks carry whole speaker
|
||||
turns (one part per turn), which join with a space.
|
||||
@@ -332,11 +337,12 @@ Settled rules:
|
||||
| OpenAI | stream (`stream: true` in `stream` mode; `whisper-1` ignores `stream`, so it emits only `finish`) | multipart `file` (inline only) | `whisper-1` (`verbose_json`); diarize model: `segment` | `gpt-4o-transcribe-diarize` (`diarized_json`) | `speakers`; `prompt` on the diarize model | `tokens` or `seconds` |
|
||||
| Gemini | stream (`generateContent` / `streamGenerateContent`) | `inlineData` or Gemini Files `fileData` | `audioTranscriptionConfig.wordTimestamp` | `audioTranscriptionConfig.diarization` | `prompt`, `speakers` | `tokens` |
|
||||
| Deepgram | inline | raw body, or JSON `{ url }` | words always; `segment` → `utterances` | `diarize_model=latest` + `utterances` | `prompt`, `speakers` | `seconds` (`metadata.duration`) |
|
||||
| ElevenLabs | inline | multipart `file`, or `source_url` | words always; `segment` → `diarize` (speaker turns) | `diarize` | `prompt`; `webhook`, per-channel `use_multi_channel` | `seconds` (`audio_duration_secs`) |
|
||||
| AssemblyAI | queued (upload → submit → poll) | `/v2/upload` then `audio_url`, or a URL | words always; `segment` → `speaker_labels` | `speaker_labels` | — | `seconds` (`audio_duration`) |
|
||||
|
||||
Deferred: `Transcription.session(...)` — realtime STT over WebSocket (Deepgram live, AssemblyAI streaming, ElevenLabs
|
||||
realtime, OpenAI realtime transcription) — is the same future scoped `session` shape as input-streaming TTS and ships
|
||||
with the realtime work in phase 5. ElevenLabs Scribe is not implemented yet.
|
||||
with the realtime work in phase 5.
|
||||
|
||||
### `Generation` — shared async execution
|
||||
|
||||
@@ -414,7 +420,7 @@ implemented):
|
||||
| `OpenAI` | responses (default), chat | Images API (stream) | *Sora skipped (decision 8)* | ✓ | ✓ | |
|
||||
| `Google` | Gemini | Gemini-native | Veo | Gemini TTS | `gemini-3.5-transcribe` | |
|
||||
| `XAI` | ✓ | ✓ | ✓ | | | |
|
||||
| `ElevenLabs` | | | | ✓ | *Scribe (pending)* | *soundEffect, music (phase 5)* |
|
||||
| `ElevenLabs` | | | | ✓ | Scribe | *soundEffect, music (phase 5)* |
|
||||
| `Cartesia` | | | | ✓ | | |
|
||||
| `Deepgram` | | | | Aura | ✓ | |
|
||||
| `Fal` | | ✓ (queued) | ✓ | | | |
|
||||
@@ -467,7 +473,7 @@ Foundation + Image ship together as the reference implementation, serially. Vide
|
||||
|
||||
1. **Foundation** — per-modality selectors, `Media`, `Generation`, `Poll`, `Usage` union, `MediaProtocol` kinds, `@opencode/ai/promise` with `llm` + `image`. Port the five existing image protocols onto it. Unify `MediaPart` and add the `media` LLM event (fixes Gemini image output being dropped).
|
||||
2. **Video** — ✅ Veo, xAI, fal, Runway shipped (`MediaProtocol.queued`, `Video.start/generate/resume/stream`, promise `ai.video`). Deferred: `Video.complete` (webhooks), Luma, Kling, MiniMax, Replicate.
|
||||
3. **Speech + Transcription** — ✅ Speech: OpenAI, Gemini TTS, ElevenLabs, Cartesia, Deepgram shipped (`MediaProtocol.stream`, `Speech.generate/stream`, promise `ai.speech`). ✅ Transcription: OpenAI, Gemini, Deepgram, AssemblyAI shipped across all three route kinds (`Transcription.generate/stream/start/resume`, promise `ai.transcription`). Pending: ElevenLabs Scribe. Deferred: `Speech.session` and `Transcription.session` (WebSocket streaming).
|
||||
3. **Speech + Transcription** — ✅ Speech: OpenAI, Gemini TTS, ElevenLabs, Cartesia, Deepgram shipped (`MediaProtocol.stream`, `Speech.generate/stream`, promise `ai.speech`). ✅ Transcription: OpenAI, Gemini, Deepgram, ElevenLabs Scribe, AssemblyAI shipped across all three route kinds (`Transcription.generate/stream/start/resume`, promise `ai.transcription`). Deferred: `Speech.session` and `Transcription.session` (WebSocket streaming).
|
||||
4. **Image queued routes and partials** — ✅ BFL, fal, Replicate, and Stability creative upscale queued; Stability generate inline; OpenAI `partial_images` streaming (`image-partial` restored). Imagen dropped: shut down on the Gemini API and discontinued on Vertex (2026-06-30). Deferred: Stability's synchronous edit and fast/conservative upscale endpoints.
|
||||
5. **Later** — ElevenLabs music/SFX, Lyria, `Speech.session` / `Transcription.session`, realtime.
|
||||
|
||||
|
||||
@@ -6,6 +6,7 @@ import { mergeJsonRecords, type OpenString } from "../schema/index.js"
|
||||
import { TranscriptionModel, TranscriptionResponse, type TranscriptionRequestFor } from "../transcription.js"
|
||||
import { ProviderShared } from "./shared.js"
|
||||
import { MediaInput } from "./utils/media-input.js"
|
||||
import { SpeakerTurns } from "./utils/speaker-turns.js"
|
||||
|
||||
const route = MediaProtocol.identity({ id: "deepgram-transcription", name: "Deepgram", provider: "deepgram" })
|
||||
export const DEFAULT_BASE_URL = "https://api.deepgram.com"
|
||||
@@ -115,16 +116,6 @@ const speaker = (value: number | undefined) => (value === undefined ? undefined
|
||||
|
||||
const wordText = (word: typeof Word.Type) => word.punctuated_word ?? word.word
|
||||
|
||||
// Utterances split on pauses, not speakers: the v2 diarizer labels a whole utterance with one speaker even when its
|
||||
// words change speaker, so segments split each utterance at speaker changes.
|
||||
const speakerTurns = (words: ReadonlyArray<typeof Word.Type>) =>
|
||||
words.reduce<Array<Array<typeof Word.Type>>>((turns, word) => {
|
||||
const last = turns.at(-1)
|
||||
if (last === undefined || last[0].speaker !== word.speaker) return [...turns, [word]]
|
||||
last.push(word)
|
||||
return turns
|
||||
}, [])
|
||||
|
||||
const decodeResponse = Effect.fn("DeepgramTranscription.decodeResponse")(function* (
|
||||
response: HttpClientResponse.HttpClientResponse,
|
||||
) {
|
||||
@@ -136,6 +127,8 @@ const decodeResponse = Effect.fn("DeepgramTranscription.decodeResponse")(functio
|
||||
const requestID = output.value.metadata?.request_id
|
||||
return new TranscriptionResponse({
|
||||
text: alternative.transcript,
|
||||
// Utterances split on pauses, not speakers: the v2 diarizer labels a whole utterance with one speaker even when
|
||||
// its words change speaker, so segments split each utterance at speaker changes.
|
||||
segments: output.value.results.utterances?.flatMap((utterance) =>
|
||||
utterance.words === undefined || utterance.words.length === 0
|
||||
? [
|
||||
@@ -146,7 +139,7 @@ const decodeResponse = Effect.fn("DeepgramTranscription.decodeResponse")(functio
|
||||
speaker: speaker(utterance.speaker),
|
||||
},
|
||||
]
|
||||
: speakerTurns(utterance.words).map((turn) => ({
|
||||
: SpeakerTurns.group(utterance.words, (word) => word.speaker).map((turn) => ({
|
||||
text: turn.map(wordText).join(" "),
|
||||
startSeconds: turn[0].start,
|
||||
endSeconds: turn[turn.length - 1].end,
|
||||
|
||||
@@ -0,0 +1,211 @@
|
||||
import { Effect, Schema } from "effect"
|
||||
import type { HttpClientResponse } from "effect/unstable/http"
|
||||
import { MediaProtocol } from "../route/media-protocol.js"
|
||||
import { MediaRoute } from "../route/media.js"
|
||||
import { mergeJsonRecords, type OpenString } from "../schema/index.js"
|
||||
import { TranscriptionModel, TranscriptionResponse, type TranscriptionRequestFor } from "../transcription.js"
|
||||
import { mediaTypeExtension } from "../utils/media-type.js"
|
||||
import { ProviderShared, optionalNull } from "./shared.js"
|
||||
import { MediaInput } from "./utils/media-input.js"
|
||||
import { SpeakerTurns } from "./utils/speaker-turns.js"
|
||||
|
||||
const route = MediaProtocol.identity({
|
||||
id: "elevenlabs-transcription",
|
||||
name: "ElevenLabs Transcription",
|
||||
provider: "elevenlabs",
|
||||
})
|
||||
export const DEFAULT_BASE_URL = "https://api.elevenlabs.io"
|
||||
export const PATH = "/v1/speech-to-text"
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
// 1. Public model input
|
||||
// ---------------------------------------------------------------------------
|
||||
|
||||
export type ElevenLabsTranscriptionOptions = {
|
||||
readonly tag_audio_events?: boolean
|
||||
readonly timestamps_granularity?: OpenString<"none" | "word" | "character">
|
||||
readonly diarization_threshold?: number
|
||||
readonly file_format?: OpenString<"pcm_s16le_16" | "other">
|
||||
readonly temperature?: number
|
||||
readonly seed?: number
|
||||
readonly keyterms?: ReadonlyArray<string>
|
||||
readonly no_verbatim?: boolean
|
||||
readonly detect_speaker_roles?: boolean
|
||||
readonly use_speaker_library?: boolean
|
||||
readonly entity_detection?: string | ReadonlyArray<string>
|
||||
readonly entity_redaction?: string | ReadonlyArray<string>
|
||||
readonly entity_redaction_mode?: OpenString<"redacted" | "entity_type" | "enumerated_entity_type">
|
||||
} & Record<string, unknown>
|
||||
|
||||
export type Request = TranscriptionRequestFor<ElevenLabsTranscriptionOptions>
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
// 2. Response schema
|
||||
// ---------------------------------------------------------------------------
|
||||
|
||||
/** `type` is `word`, `spacing` (the whitespace between words), or `audio_event` (`(laughter)`). */
|
||||
const Token = Schema.Struct({
|
||||
text: Schema.String,
|
||||
type: Schema.String,
|
||||
start: optionalNull(Schema.Number),
|
||||
end: optionalNull(Schema.Number),
|
||||
speaker_id: optionalNull(Schema.String),
|
||||
logprob: optionalNull(Schema.Number),
|
||||
})
|
||||
type Token = Schema.Schema.Type<typeof Token>
|
||||
|
||||
const Transcript = Schema.Struct({
|
||||
language_code: optionalNull(Schema.String),
|
||||
text: Schema.String,
|
||||
words: optionalNull(Schema.Array(Token)),
|
||||
transcription_id: optionalNull(Schema.String),
|
||||
audio_duration_secs: optionalNull(Schema.Number),
|
||||
})
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
// 5. Request body construction
|
||||
// ---------------------------------------------------------------------------
|
||||
|
||||
/** Speaker turns are the only segments ElevenLabs can produce, and `num_speakers` only applies to diarization. */
|
||||
const diarizes = (request: Request) =>
|
||||
request.diarize === true || request.timestamps === "segment" || request.speakers !== undefined
|
||||
|
||||
const RESERVED_FORM_FIELDS = new Set([
|
||||
"file",
|
||||
"cloud_storage_url",
|
||||
"source_url",
|
||||
"model_id",
|
||||
"language_code",
|
||||
"diarize",
|
||||
"num_speakers",
|
||||
])
|
||||
|
||||
const validate = (request: Request, overlay: Record<string, unknown>) => {
|
||||
// Webhook requests return 202 with no transcript; the result arrives at a configured webhook instead.
|
||||
if (overlay.webhook === true)
|
||||
return Effect.fail(route.unsupported("transcription.webhook", `${route.name} does not deliver to webhooks`))
|
||||
// Separate multichannel output replaces the transcript with one transcript per channel.
|
||||
if (overlay.use_multi_channel === true && overlay.multichannel_output_style !== "combined")
|
||||
return Effect.fail(
|
||||
route.unsupported(
|
||||
"transcription.multichannel",
|
||||
`${route.name} returns a single transcript; set multichannel_output_style: "combined" to merge channels`,
|
||||
),
|
||||
)
|
||||
if (overlay.timestamps_granularity === "none" && (request.timestamps === "word" || diarizes(request)))
|
||||
return Effect.fail(
|
||||
route.unsupported(
|
||||
"media.timestamps",
|
||||
`${route.name} cannot return word timestamps or speaker turns with timestamps_granularity: "none"`,
|
||||
),
|
||||
)
|
||||
return Effect.void
|
||||
}
|
||||
|
||||
const fromRequest = Effect.fn("ElevenLabsTranscription.fromRequest")(function* (request: Request) {
|
||||
const overlay = mergeJsonRecords(request.providerOptions, request.http?.body) ?? {}
|
||||
yield* validate(request, overlay)
|
||||
const form = new FormData()
|
||||
const url = ProviderShared.mediaUrl(request.audio)
|
||||
if (url === undefined) {
|
||||
const extension = mediaTypeExtension(request.audio.mediaType)
|
||||
const audio = yield* MediaInput.inlineBytes(route.id, request.audio)
|
||||
form.append(
|
||||
"file",
|
||||
MediaInput.blob(audio, request.audio.mediaType),
|
||||
extension === undefined ? "audio" : `audio.${extension}`,
|
||||
)
|
||||
}
|
||||
MediaInput.appendFields(
|
||||
form,
|
||||
{
|
||||
model_id: request.model.id,
|
||||
// `cloud_storage_url` is deprecated in favor of `source_url`, which accepts any hosted audio or video URL.
|
||||
source_url: url,
|
||||
language_code: request.language,
|
||||
diarize: diarizes(request) ? true : undefined,
|
||||
num_speakers: request.speakers,
|
||||
},
|
||||
{ overlay, reserved: RESERVED_FORM_FIELDS, repeatArrays: "key" },
|
||||
)
|
||||
return MediaProtocol.multipart(form)
|
||||
})
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
// 6. Response decoding
|
||||
// ---------------------------------------------------------------------------
|
||||
|
||||
const decodeTranscript = route.decodeJson(Transcript)
|
||||
|
||||
type TimedWord = Token & { readonly start: number; readonly end: number }
|
||||
|
||||
const isTimedWord = (token: Token): token is TimedWord =>
|
||||
token.type === "word" && typeof token.start === "number" && typeof token.end === "number"
|
||||
|
||||
/** Turn text keeps the provider's own spacing tokens, so languages written without spaces are not re-spaced. */
|
||||
const speakerTurns = (tokens: ReadonlyArray<Token>) =>
|
||||
SpeakerTurns.group(
|
||||
tokens.filter((token) => token.type === "word" || token.type === "spacing"),
|
||||
(token) => token.speaker_id,
|
||||
).flatMap((turn) => {
|
||||
const words = turn.filter(isTimedWord)
|
||||
if (words.length === 0) return []
|
||||
return [
|
||||
{
|
||||
text: turn
|
||||
.map((token) => token.text)
|
||||
.join("")
|
||||
.trim(),
|
||||
startSeconds: words[0].start,
|
||||
endSeconds: words[words.length - 1].end,
|
||||
speaker: turn[0].speaker_id ?? undefined,
|
||||
},
|
||||
]
|
||||
})
|
||||
|
||||
const decodeResponse = Effect.fn("ElevenLabsTranscription.decodeResponse")(function* (
|
||||
response: HttpClientResponse.HttpClientResponse,
|
||||
context: MediaProtocol.DecodeContext<Request>,
|
||||
) {
|
||||
const output = yield* decodeTranscript(response)
|
||||
const transcript = output.value
|
||||
const tokens = transcript.words ?? []
|
||||
const duration = transcript.audio_duration_secs ?? undefined
|
||||
const transcriptionID = transcript.transcription_id ?? undefined
|
||||
return new TranscriptionResponse({
|
||||
text: transcript.text,
|
||||
segments: diarizes(context.request) ? speakerTurns(tokens) : undefined,
|
||||
words: tokens.filter(isTimedWord).map((word) => ({
|
||||
text: word.text,
|
||||
startSeconds: word.start,
|
||||
endSeconds: word.end,
|
||||
speaker: word.speaker_id ?? undefined,
|
||||
confidence: typeof word.logprob === "number" ? Math.exp(word.logprob) : undefined,
|
||||
})),
|
||||
language: transcript.language_code?.toLowerCase(),
|
||||
durationSeconds: duration,
|
||||
usage: duration === undefined ? undefined : { type: "seconds", seconds: duration },
|
||||
providerMetadata: transcriptionID === undefined ? undefined : { elevenlabs: { transcriptionId: transcriptionID } },
|
||||
})
|
||||
})
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
// 7. Protocol and route
|
||||
// ---------------------------------------------------------------------------
|
||||
|
||||
export const protocol = MediaProtocol.inline<Request, TranscriptionResponse>(route, {
|
||||
unsupported: ["prompt"],
|
||||
body: { from: fromRequest },
|
||||
response: { decode: decodeResponse },
|
||||
})
|
||||
|
||||
export const model = (input: MediaRoute.ModelInput) =>
|
||||
TranscriptionModel.fromRoute<ElevenLabsTranscriptionOptions>(
|
||||
{ protocol, baseURL: DEFAULT_BASE_URL, path: PATH },
|
||||
input,
|
||||
)
|
||||
|
||||
export const ElevenLabsTranscription = {
|
||||
protocol,
|
||||
model,
|
||||
} as const
|
||||
@@ -193,7 +193,7 @@ const fromRequest = Effect.fn("OpenAITranscription.fromRequest")(function* (requ
|
||||
{
|
||||
overlay: mergeJsonRecords(request.providerOptions, request.http?.body),
|
||||
reserved: RESERVED_FORM_FIELDS,
|
||||
repeatArrays: true,
|
||||
repeatArrays: "key[]",
|
||||
},
|
||||
)
|
||||
return MediaProtocol.multipart(form)
|
||||
|
||||
@@ -71,8 +71,9 @@ export const imageOutput = (
|
||||
}
|
||||
|
||||
/**
|
||||
* Append multipart text fields: strings as-is, other values as JSON, or arrays as repeated `key[]` parts with
|
||||
* `repeatArrays`. `overlay` keys in `reserved` are dropped so `http.body` cannot replace route-owned fields.
|
||||
* Append multipart text fields: strings as-is, other values as JSON, or scalar arrays as one part per item with
|
||||
* `repeatArrays`, named `key[]` or `key`. `overlay` keys in `reserved` are dropped so `http.body` cannot replace
|
||||
* route-owned fields.
|
||||
*/
|
||||
export const appendFields = (
|
||||
form: FormData,
|
||||
@@ -80,13 +81,13 @@ export const appendFields = (
|
||||
options: {
|
||||
readonly overlay?: Record<string, unknown>
|
||||
readonly reserved: ReadonlySet<string>
|
||||
readonly repeatArrays?: true
|
||||
readonly repeatArrays?: "key[]" | "key"
|
||||
},
|
||||
) => {
|
||||
const overlay = Object.entries(options.overlay ?? {}).filter(([key]) => !options.reserved.has(key))
|
||||
Object.entries(mergeJsonRecords(fields, Object.fromEntries(overlay)) ?? {}).forEach(([key, value]) => {
|
||||
if (Array.isArray(value) && options.repeatArrays)
|
||||
return value.forEach((item) => form.append(`${key}[]`, String(item)))
|
||||
if (Array.isArray(value) && value.every(isScalar) && options.repeatArrays !== undefined)
|
||||
return value.forEach((item) => form.append(options.repeatArrays === "key[]" ? `${key}[]` : key, String(item)))
|
||||
form.append(key, typeof value === "string" ? value : encodeJson(value))
|
||||
})
|
||||
}
|
||||
|
||||
@@ -0,0 +1,10 @@
|
||||
/** Split an ordered token list into runs of consecutive tokens with the same speaker. */
|
||||
export const group = <Item>(items: ReadonlyArray<Item>, speaker: (item: Item) => unknown) =>
|
||||
items.reduce<Array<Array<Item>>>((turns, item) => {
|
||||
const last = turns.at(-1)
|
||||
if (last === undefined || speaker(last[0]) !== speaker(item)) return [...turns, [item]]
|
||||
last.push(item)
|
||||
return turns
|
||||
}, [])
|
||||
|
||||
export * as SpeakerTurns from "./speaker-turns.js"
|
||||
@@ -3,8 +3,10 @@ import type { ProviderAuthOption } from "../route/auth-options.js"
|
||||
import { MediaRoute } from "../route/media.js"
|
||||
import { type HttpOptions, ProviderID, type ModelID } from "../schema/index.js"
|
||||
import { ElevenLabsSpeech } from "../protocols/elevenlabs-speech.js"
|
||||
import { ElevenLabsTranscription } from "../protocols/elevenlabs-transcription.js"
|
||||
|
||||
export type { ElevenLabsOutputFormat, ElevenLabsSpeechOptions } from "../protocols/elevenlabs-speech.js"
|
||||
export type { ElevenLabsTranscriptionOptions } from "../protocols/elevenlabs-transcription.js"
|
||||
|
||||
export const id = ProviderID.make("elevenlabs")
|
||||
|
||||
@@ -24,12 +26,15 @@ const auth = (options: ProviderAuthOption<"optional">) => {
|
||||
export const configure = (input: Config = {}) => {
|
||||
const media = MediaRoute.deployment(input, auth(input))
|
||||
const speech = (modelID: string | ModelID) => ElevenLabsSpeech.model({ ...media, id: modelID })
|
||||
const transcription = (modelID: string | ModelID) => ElevenLabsTranscription.model({ ...media, id: modelID })
|
||||
return {
|
||||
id,
|
||||
speech,
|
||||
transcription,
|
||||
configure,
|
||||
}
|
||||
}
|
||||
|
||||
export const provider = configure()
|
||||
export const speech = provider.speech
|
||||
export const transcription = provider.transcription
|
||||
|
||||
@@ -103,7 +103,7 @@ export type TranscriptionRequestInput<Model extends TranscriptionModel = Transcr
|
||||
// Response and events
|
||||
// ---------------------------------------------------------------------------
|
||||
|
||||
/** Speaker labels are provider-native (`A`, `0`, `spk:0`, or a known speaker name). */
|
||||
/** Speaker labels are provider-native (`A`, `0`, `spk:0`, `speaker_0`, or a known speaker name). */
|
||||
export const TranscriptionSegment = Schema.Struct({
|
||||
text: Schema.String,
|
||||
startSeconds: Schema.Number,
|
||||
|
||||
@@ -197,6 +197,11 @@ describe("public exports", () => {
|
||||
expect(Google.configure({ apiKey: "fixture" }).transcription("gemini-3.5-transcribe").route.kind).toBe("stream")
|
||||
expect(Deepgram.configure({ apiKey: "fixture" }).transcription("nova-3").route.kind).toBe("inline")
|
||||
expect(AssemblyAI.configure({ apiKey: "fixture" }).transcription("universal-3-5-pro").route.kind).toBe("queued")
|
||||
expect(ElevenLabs.configure({ apiKey: "fixture" }).transcription("scribe_v2").route.id).toBe(
|
||||
"elevenlabs-transcription",
|
||||
)
|
||||
expect(ElevenLabs.configure({ apiKey: "fixture" }).transcription("scribe_v2").route.kind).toBe("inline")
|
||||
expect(ElevenLabs.provider.transcription).toBe(ElevenLabs.transcription)
|
||||
})
|
||||
|
||||
test("protocol barrels expose supported low-level routes", () => {
|
||||
|
||||
+32
@@ -0,0 +1,32 @@
|
||||
{
|
||||
"version": 1,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"prefix:elevenlabs-transcription",
|
||||
"provider:elevenlabs",
|
||||
"protocol:elevenlabs-transcription"
|
||||
],
|
||||
"name": "elevenlabs-transcription/groups-diarized-words-into-speaker-turns",
|
||||
"recordedAt": "2026-09-27T09:35:28.265Z"
|
||||
},
|
||||
"interactions": [
|
||||
{
|
||||
"transport": "http",
|
||||
"request": {
|
||||
"method": "POST",
|
||||
"url": "https://api.elevenlabs.io/v1/speech-to-text",
|
||||
"headers": {
|
||||
"content-type": "multipart/form-data; boundary=----WebKitFormBoundary356bdc14864a477dbacbfcf60d1ecceb"
|
||||
},
|
||||
"body": "--BOUNDARY\r\nContent-Disposition: form-data; name=\"file\"; filename=\"audio.mp3\"\r\nContent-Type: audio/mpeg\r\n\r\n[audio]\r\n--BOUNDARY\r\nContent-Disposition: form-data; name=\"model_id\"\r\n\r\nscribe_v2\r\n--BOUNDARY\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\ntrue\r\n--BOUNDARY--\r\n"
|
||||
},
|
||||
"response": {
|
||||
"status": 200,
|
||||
"headers": {
|
||||
"content-type": "application/json"
|
||||
},
|
||||
"body": "{\"language_code\":\"eng\",\"language_probability\":0.9495430588722229,\"text\":\"Did the release ship? Yes, it shipped this morning\",\"words\":[{\"text\":\"Did\",\"start\":0.34,\"end\":0.44,\"type\":\"word\",\"speaker_id\":\"speaker_0\",\"logprob\":-1.7881377516459906e-6},{\"text\":\" \",\"start\":0.44,\"end\":0.48,\"type\":\"spacing\",\"speaker_id\":\"speaker_0\",\"logprob\":-1.1920928244535389e-7},{\"text\":\"the\",\"start\":0.48,\"end\":0.56,\"type\":\"word\",\"speaker_id\":\"speaker_0\",\"logprob\":-1.1920928244535389e-7},{\"text\":\" \",\"start\":0.56,\"end\":0.6,\"type\":\"spacing\",\"speaker_id\":\"speaker_0\",\"logprob\":-7.152531907195225e-6},{\"text\":\"release\",\"start\":0.6,\"end\":0.92,\"type\":\"word\",\"speaker_id\":\"speaker_0\",\"logprob\":-7.152531907195225e-6},{\"text\":\" \",\"start\":0.92,\"end\":0.94,\"type\":\"spacing\",\"speaker_id\":\"speaker_0\",\"logprob\":-8.344646857949556e-7},{\"text\":\"ship?\",\"start\":0.94,\"end\":1.26,\"type\":\"word\",\"speaker_id\":\"speaker_0\",\"logprob\":-7.414704032271402e-6},{\"text\":\" \",\"start\":1.26,\"end\":1.26,\"type\":\"spacing\",\"speaker_id\":\"speaker_0\",\"logprob\":-0.0009363081189803779},{\"text\":\"Yes,\",\"start\":1.68,\"end\":2.02,\"type\":\"word\",\"speaker_id\":\"speaker_1\",\"logprob\":-0.003542040009030245},{\"text\":\" \",\"start\":2.02,\"end\":2.48,\"type\":\"spacing\",\"speaker_id\":\"speaker_1\",\"logprob\":-3.933898824470816e-6},{\"text\":\"it\",\"start\":2.48,\"end\":2.62,\"type\":\"word\",\"speaker_id\":\"speaker_1\",\"logprob\":-3.933898824470816e-6},{\"text\":\" \",\"start\":2.62,\"end\":2.64,\"type\":\"spacing\",\"speaker_id\":\"speaker_1\",\"logprob\":-0.000013589766240329482},{\"text\":\"shipped\",\"start\":2.66,\"end\":2.9,\"type\":\"word\",\"speaker_id\":\"speaker_1\",\"logprob\":-0.000013589766240329482},{\"text\":\" \",\"start\":2.9,\"end\":2.94,\"type\":\"spacing\",\"speaker_id\":\"speaker_1\",\"logprob\":0.0},{\"text\":\"this\",\"start\":2.94,\"end\":3.12,\"type\":\"word\",\"speaker_id\":\"speaker_1\",\"logprob\":0.0},{\"text\":\" \",\"start\":3.12,\"end\":3.18,\"type\":\"spacing\",\"speaker_id\":\"speaker_1\",\"logprob\":-3.576278118089249e-7},{\"text\":\"morning\",\"start\":3.18,\"end\":3.5,\"type\":\"word\",\"speaker_id\":\"speaker_1\",\"logprob\":-3.576278118089249e-7}],\"transcription_id\":\"cs3I2282TH8hjw12brNg\",\"audio_duration_secs\":3.5526875}"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
+50
@@ -0,0 +1,50 @@
|
||||
{
|
||||
"version": 1,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"prefix:elevenlabs-transcription",
|
||||
"provider:elevenlabs",
|
||||
"protocol:elevenlabs-transcription"
|
||||
],
|
||||
"name": "elevenlabs-transcription/transcribes-audio-with-word-timestamps",
|
||||
"recordedAt": "2026-09-27T09:35:27.686Z"
|
||||
},
|
||||
"interactions": [
|
||||
{
|
||||
"transport": "http",
|
||||
"request": {
|
||||
"method": "POST",
|
||||
"url": "https://api.elevenlabs.io/v1/speech-to-text",
|
||||
"headers": {
|
||||
"content-type": "multipart/form-data; boundary=----WebKitFormBoundarye2be7b31e94441bbbeb35a9c890a9d74"
|
||||
},
|
||||
"body": "--BOUNDARY\r\nContent-Disposition: form-data; name=\"file\"; filename=\"audio.mp3\"\r\nContent-Type: audio/mpeg\r\n\r\n[audio]\r\n--BOUNDARY\r\nContent-Disposition: form-data; name=\"model_id\"\r\n\r\nscribe_v2\r\n--BOUNDARY--\r\n"
|
||||
},
|
||||
"response": {
|
||||
"status": 200,
|
||||
"headers": {
|
||||
"content-type": "application/json"
|
||||
},
|
||||
"body": "{\"language_code\":\"eng\",\"language_probability\":0.6618340611457825,\"text\":\"Hello from OpenCode\",\"words\":[{\"text\":\"Hello\",\"start\":0.4,\"end\":0.66,\"type\":\"word\",\"logprob\":-0.000014781842764932662},{\"text\":\" \",\"start\":0.66,\"end\":0.74,\"type\":\"spacing\",\"logprob\":-3.814689989667386e-6},{\"text\":\"from\",\"start\":0.74,\"end\":0.84,\"type\":\"word\",\"logprob\":-3.814689989667386e-6},{\"text\":\" \",\"start\":0.84,\"end\":0.9,\"type\":\"spacing\",\"logprob\":-0.018268775194883347},{\"text\":\"OpenCode\",\"start\":0.9,\"end\":1.44,\"type\":\"word\",\"logprob\":-0.1251817401498556}],\"transcription_id\":\"D4VfnANM2ArCHTujIb9q\",\"audio_duration_secs\":1.54125}"
|
||||
}
|
||||
},
|
||||
{
|
||||
"transport": "http",
|
||||
"request": {
|
||||
"method": "POST",
|
||||
"url": "https://api.elevenlabs.io/v1/speech-to-text",
|
||||
"headers": {
|
||||
"content-type": "multipart/form-data; boundary=----WebKitFormBoundaryfb80d0e44d9e44d299416ed546a04056"
|
||||
},
|
||||
"body": "--BOUNDARY\r\nContent-Disposition: form-data; name=\"file\"; filename=\"audio.mp3\"\r\nContent-Type: audio/mpeg\r\n\r\n[audio]\r\n--BOUNDARY\r\nContent-Disposition: form-data; name=\"model_id\"\r\n\r\nscribe_v2\r\n--BOUNDARY--\r\n"
|
||||
},
|
||||
"response": {
|
||||
"status": 200,
|
||||
"headers": {
|
||||
"content-type": "application/json"
|
||||
},
|
||||
"body": "{\"language_code\":\"eng\",\"language_probability\":0.6618340611457825,\"text\":\"Hello from OpenCode\",\"words\":[{\"text\":\"Hello\",\"start\":0.4,\"end\":0.66,\"type\":\"word\",\"logprob\":-0.000023007127310847864},{\"text\":\" \",\"start\":0.66,\"end\":0.74,\"type\":\"spacing\",\"logprob\":-2.3841830625315197e-6},{\"text\":\"from\",\"start\":0.74,\"end\":0.84,\"type\":\"word\",\"logprob\":-2.3841830625315197e-6},{\"text\":\" \",\"start\":0.84,\"end\":0.9,\"type\":\"spacing\",\"logprob\":-0.008306833915412426},{\"text\":\"OpenCode\",\"start\":0.9,\"end\":1.44,\"type\":\"word\",\"logprob\":-0.1075385226868093}],\"transcription_id\":\"SkYplzfq1DW8Ae3bWnoy\",\"audio_duration_secs\":1.54125}"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,50 @@
|
||||
import { describe, expect } from "bun:test"
|
||||
import { Effect, Stream } from "effect"
|
||||
import { Transcription } from "../../src/index.js"
|
||||
import { ElevenLabs } from "../../src/providers.js"
|
||||
import { recordedTests } from "../recorded-test.js"
|
||||
import { TRANSCRIPT, audio, audioRecording, dialog } from "./transcription-recording.js"
|
||||
|
||||
const model = ElevenLabs.configure({ apiKey: process.env.ELEVENLABS_API_KEY ?? "fixture" }).transcription("scribe_v2")
|
||||
|
||||
const recorded = recordedTests({
|
||||
prefix: "elevenlabs-transcription",
|
||||
provider: "elevenlabs",
|
||||
protocol: "elevenlabs-transcription",
|
||||
requires: ["ELEVENLABS_API_KEY"],
|
||||
options: audioRecording,
|
||||
})
|
||||
|
||||
describe("ElevenLabs Transcription recorded", () => {
|
||||
recorded.effect("transcribes audio with word timestamps", () =>
|
||||
Effect.gen(function* () {
|
||||
const request = Transcription.request({ model, audio: yield* audio, timestamps: "word" })
|
||||
const response = yield* Transcription.generate(request)
|
||||
|
||||
expect(response.text).toMatch(TRANSCRIPT)
|
||||
expect(response.words?.map((word) => word.text)).toEqual(["Hello", "from", "OpenCode"])
|
||||
expect(response.words?.every((word) => word.speaker === undefined && (word.confidence ?? 0) > 0)).toBe(true)
|
||||
expect(response.segments).toBeUndefined()
|
||||
expect(response.language).toBe("eng")
|
||||
expect(response.durationSeconds).toBeGreaterThan(0)
|
||||
expect(response.usage).toEqual({ type: "seconds", seconds: response.durationSeconds })
|
||||
expect(response.providerMetadata?.elevenlabs?.transcriptionId).toEqual(expect.any(String))
|
||||
|
||||
const events = Array.from(yield* Stream.runCollect(Transcription.stream(request)))
|
||||
expect(events.map((event) => event.type)).toEqual(["finish"])
|
||||
}),
|
||||
)
|
||||
|
||||
recorded.effect("groups diarized words into speaker turns", () =>
|
||||
Effect.gen(function* () {
|
||||
const response = yield* Transcription.generate({ model, audio: yield* dialog, diarize: true })
|
||||
|
||||
expect(response.segments?.map((segment) => segment.speaker)).toEqual(["speaker_0", "speaker_1"])
|
||||
expect(response.segments?.[0].text).toMatch(/^Did the release ship\?$/)
|
||||
expect(response.segments?.[1].text).toMatch(/^Yes, it shipped this morning\.?$/)
|
||||
expect(response.segments?.map((segment) => segment.text).join(" ")).toBe(response.text)
|
||||
expect(response.words?.some((word) => word.text.trim() === "")).toBe(false)
|
||||
expect(new Set(response.words?.map((word) => word.speaker))).toEqual(new Set(["speaker_0", "speaker_1"]))
|
||||
}),
|
||||
)
|
||||
})
|
||||
@@ -3,7 +3,7 @@ import { Effect, Fiber, Layer, Stream } from "effect"
|
||||
import * as TestClock from "effect/testing/TestClock"
|
||||
import { HttpClientRequest } from "effect/unstable/http"
|
||||
import { Media, Transcription, TranscriptionClient, type TranscriptionEvent } from "../src/index.js"
|
||||
import { AssemblyAI, Deepgram, Google, OpenAI } from "../src/providers.js"
|
||||
import { AssemblyAI, Deepgram, ElevenLabs, Google, OpenAI } from "../src/providers.js"
|
||||
import { it } from "./lib/effect.js"
|
||||
import { dynamicResponse, json, observe, type Call } from "./lib/http.js"
|
||||
import { sseEvents } from "./lib/sse.js"
|
||||
@@ -35,6 +35,9 @@ const formFields = (call: Call) =>
|
||||
const assemblyai = AssemblyAI.configure({ apiKey: "aai-key", baseURL: "https://assemblyai.test" }).transcription(
|
||||
"universal-3-5-pro",
|
||||
)
|
||||
const elevenlabs = ElevenLabs.configure({ apiKey: "test", baseURL: "https://elevenlabs.test" }).transcription(
|
||||
"scribe_v2",
|
||||
)
|
||||
|
||||
describe("Transcription", () => {
|
||||
it.effect("rejects what a route cannot honor before sending anything", () =>
|
||||
@@ -459,6 +462,115 @@ describe("Transcription", () => {
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("rejects ElevenLabs prompts, webhooks, per-channel transcripts, and untimed diarization", () =>
|
||||
Effect.gen(function* () {
|
||||
const errors = yield* Effect.all(
|
||||
[
|
||||
Transcription.generate({ model: elevenlabs, audio, prompt: "OpenCode" }),
|
||||
Transcription.generate({ model: elevenlabs, audio, providerOptions: { webhook: true } }),
|
||||
Transcription.generate({ model: elevenlabs, audio, http: { body: { use_multi_channel: true } } }),
|
||||
Transcription.generate({
|
||||
model: elevenlabs,
|
||||
audio,
|
||||
diarize: true,
|
||||
providerOptions: { timestamps_granularity: "none" },
|
||||
}),
|
||||
Transcription.generate({
|
||||
model: elevenlabs,
|
||||
audio: Media.ref("file_1", { provider: "elevenlabs", mediaType: "audio/mpeg" }),
|
||||
}),
|
||||
].map((effect) => Effect.flip(effect)),
|
||||
)
|
||||
expect(errors.map((error) => [error.reason._tag, "operation" in error.reason && error.reason.operation])).toEqual(
|
||||
[
|
||||
["UnsupportedOperation", "media.prompt"],
|
||||
["UnsupportedOperation", "transcription.webhook"],
|
||||
["UnsupportedOperation", "transcription.multichannel"],
|
||||
["UnsupportedOperation", "media.timestamps"],
|
||||
["InvalidRequest", false],
|
||||
],
|
||||
)
|
||||
}).pipe(Effect.provide(layer(() => Effect.die("an unsupported request reached the network")))),
|
||||
)
|
||||
|
||||
it.effect("sends ElevenLabs URL audio as source_url and groups diarized words into speaker turns", () =>
|
||||
Effect.gen(function* () {
|
||||
const calls: Array<Call> = []
|
||||
const token = (text: string, type: string, start: number, end: number, speaker_id?: string) => ({
|
||||
text,
|
||||
type,
|
||||
start,
|
||||
end,
|
||||
speaker_id,
|
||||
logprob: 0,
|
||||
})
|
||||
const response = yield* Transcription.generate({
|
||||
model: elevenlabs,
|
||||
audio: Media.url("https://a.test/call.mp3"),
|
||||
language: "en",
|
||||
speakers: 2,
|
||||
providerOptions: { keyterms: ["OpenCode", "Scribe"], tag_audio_events: true, diarize: false },
|
||||
}).pipe(
|
||||
Effect.provide(
|
||||
layer((input) =>
|
||||
observe(calls, input).pipe(
|
||||
Effect.as(
|
||||
json(input, {
|
||||
language_code: "ENG",
|
||||
text: "Ready? (laughs) Yes. Go",
|
||||
words: [
|
||||
token("Ready?", "word", 0, 0.5, "speaker_0"),
|
||||
token(" ", "spacing", 0.5, 0.6, "speaker_0"),
|
||||
token("(laughs)", "audio_event", 0.6, 1, "speaker_0"),
|
||||
token(" ", "spacing", 1, 1.1, "speaker_0"),
|
||||
token("Yes.", "word", 1.2, 1.5, "speaker_1"),
|
||||
token(" ", "spacing", 1.5, 1.6, "speaker_1"),
|
||||
token("Go", "word", 1.6, 1.9, "speaker_0"),
|
||||
],
|
||||
transcription_id: "tr_1",
|
||||
audio_duration_secs: 2,
|
||||
}),
|
||||
),
|
||||
),
|
||||
),
|
||||
),
|
||||
)
|
||||
|
||||
// `observe` re-encodes the FormData with a new boundary, so read the boundary from the sent body.
|
||||
const boundary = /^--(\S+)/.exec(calls[0].body)?.[1]
|
||||
const form = yield* Effect.promise(() =>
|
||||
new Response(calls[0].body, {
|
||||
headers: { "content-type": `multipart/form-data; boundary=${boundary}` },
|
||||
}).formData(),
|
||||
)
|
||||
expect(calls[0].url).toBe("https://elevenlabs.test/v1/speech-to-text")
|
||||
expect(calls[0].headers.get("xi-api-key")).toBe("test")
|
||||
expect(Array.from(form.entries())).toEqual([
|
||||
["model_id", "scribe_v2"],
|
||||
["source_url", "https://a.test/call.mp3"],
|
||||
["language_code", "en"],
|
||||
["diarize", "true"],
|
||||
["num_speakers", "2"],
|
||||
["keyterms", "OpenCode"],
|
||||
["keyterms", "Scribe"],
|
||||
["tag_audio_events", "true"],
|
||||
])
|
||||
expect(response.segments).toEqual([
|
||||
{ text: "Ready?", startSeconds: 0, endSeconds: 0.5, speaker: "speaker_0" },
|
||||
{ text: "Yes.", startSeconds: 1.2, endSeconds: 1.5, speaker: "speaker_1" },
|
||||
{ text: "Go", startSeconds: 1.6, endSeconds: 1.9, speaker: "speaker_0" },
|
||||
])
|
||||
expect(response.words?.map((word) => [word.text, word.speaker, word.confidence])).toEqual([
|
||||
["Ready?", "speaker_0", 1],
|
||||
["Yes.", "speaker_1", 1],
|
||||
["Go", "speaker_0", 1],
|
||||
])
|
||||
expect(response.language).toBe("eng")
|
||||
expect(response.usage).toEqual({ type: "seconds", seconds: 2 })
|
||||
expect(response.providerMetadata).toEqual({ elevenlabs: { transcriptionId: "tr_1" } })
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("rejects reading an AssemblyAI result before the transcript finishes", () =>
|
||||
Effect.gen(function* () {
|
||||
const generation = yield* Transcription.resume(assemblyai, { transcriptID: "tr_1" })
|
||||
|
||||
Reference in New Issue
Block a user