ElevenLabs Speech to Text with Scribe V2: Transcribe audio with improved accuracy.
Transforms spoken audio into text with word-level timestamps and optional speaker identification. Supports 99 languages with state-of-the-art accuracy. Scribe V2 offers improved performance and supports keyterms for biasing transcription.
The client provides a convenient way to interact with the model API.
npm install --save @fal-ai/clientSet FAL_KEY as an environment variable in your runtime.
export FAL_KEY="YOUR_API_KEY"The client API handles the API submit protocol. It will handle the request status updates and return the result when the request is completed.
import { fal } from "@fal-ai/client";
const result = await fal.subscribe("fal-ai/elevenlabs/speech-to-text/scribe-v2", {
input: {
audio_url: "https://storage.googleapis.com/falserverless/example_inputs/elevenlabs/scribe_v2_in.mp3"
},
logs: true,
onQueueUpdate: (update) => {
if (update.status === "IN_PROGRESS") {
update.logs.map((log) => log.message).forEach(console.log);
}
},
});
console.log(result.data);
console.log(result.requestId);The API uses an API Key for authentication. It is recommended you set the FAL_KEY environment variable in your runtime when possible.
import { fal } from "@fal-ai/client";
fal.config({
credentials: "YOUR_FAL_KEY"
});The client API provides a convenient way to submit requests to the model.
import { fal } from "@fal-ai/client";
const { request_id } = await fal.queue.submit("fal-ai/elevenlabs/speech-to-text/scribe-v2", {
input: {
audio_url: "https://storage.googleapis.com/falserverless/example_inputs/elevenlabs/scribe_v2_in.mp3"
},
webhookUrl: "https://optional.webhook.url/for/results",
});You can fetch the status of a request to check if it is completed or still in progress.
import { fal } from "@fal-ai/client";
const status = await fal.queue.status("fal-ai/elevenlabs/speech-to-text/scribe-v2", {
requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b",
logs: true,
});Once the request is completed, you can fetch the result. See the Output Schema for the expected result format.
import { fal } from "@fal-ai/client";
const result = await fal.queue.result("fal-ai/elevenlabs/speech-to-text/scribe-v2", {
requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b"
});
console.log(result.data);
console.log(result.requestId);Some attributes in the API accept file URLs as input. Whenever that's the case you can pass your own URL or a Base64 data URI.
You can pass a Base64 data URI as a file input. The API will handle the file decoding for you. Keep in mind that for large files, this alternative although convenient can impact the request performance.
You can also pass your own URLs as long as they are publicly accessible. Be aware that some hosts might block cross-site requests, rate-limit, or consider the request as a bot.
We provide a convenient file storage that allows you to upload files and use them in your requests. You can upload files using the client API and use the returned URL in your requests.
import { fal } from "@fal-ai/client";
const file = new File(["Hello, World!"], "hello.txt", { type: "text/plain" });
const url = await fal.storage.upload(file);Read more about file handling in our file upload guide.
audio_url string* requiredURL of the audio file to transcribe
language_code stringLanguage code of the audio
tag_audio_events booleanTag audio events like laughter, applause, etc. Default value: true
diarize booleanWhether to annotate who is speaking Default value: true
Words or sentences to bias the model towards transcribing. Up to 100 keyterms, max 50 characters each. Adds 30% premium over base transcription price.
{
"audio_url": "https://storage.googleapis.com/falserverless/example_inputs/elevenlabs/scribe_v2_in.mp3",
"language_code": "eng",
"tag_audio_events": true,
"diarize": true,
"keyterms": []
}text string* requiredThe full transcribed text
language_code string* requiredDetected or specified language code
language_probability float* requiredConfidence in language detection
Word-level transcription details
{
"text": "Hey, this is a test recording for Scribe version two, which is now available on fal.ai.",
"language_code": "eng",
"language_probability": 1,
"words": {
"type": "word",
"end": 0.539,
"start": 0.079,
"text": "Hey,",
"speaker_id": "speaker_0"
}
}text string* requiredThe transcribed word or audio event
start floatStart time in seconds
end floatEnd time in seconds
type string* requiredType of element (word, spacing, or audio_event)
speaker_id stringSpeaker identifier if diarization was enabled