Entity detection

{
  "language_code": "eng",
  "language_probability": 0.9869821071624756,
  "text": "My name is Jill. My date of birth is the 12th of July 1987, and my credit card number is 4242-4242-4242-4242.",
  "words": [
    { "text": "My", "start": 0.099, "end": 0.259, "type": "word", "logprob": 0.0 },
    { "text": " ", "start": 0.259, "end": 0.299, "type": "spacing", "logprob": 0.0 },
    { "text": "name", "start": 0.299, "end": 0.42, "type": "word", "logprob": 0.0 },
    ...
  ],
  "transcription_id": "Y2ZX8AxHUzTPCIualYiE",
  "entities": [
    {
      "text": "Jill",
      "entity_type": "name",
      "start_char": 11,
      "end_char": 15
    },
    {
      "text": "12th of July 1987",
      "entity_type": "dob",
      "start_char": 41,
      "end_char": 58
    },
    {
      "text": "4242-4242-4242-4242",
      "entity_type": "credit_card",
      "start_char": 89,
      "end_char": 108
    }
  ]
}

import os
from dotenv import load_dotenv
from io import BytesIO
import requests
from elevenlabs.client import ElevenLabs

load_dotenv()

elevenlabs = ElevenLabs(
    api_key=os.getenv("ELEVENLABS_API_KEY"),
)

audio_url = (
    "https://storage.googleapis.com/eleven-public-cdn/documentation_assets/audio/stt-entity-detection-pii.mp3"
)
response = requests.get(audio_url)
audio_data = BytesIO(response.content)

transcription = elevenlabs.speech_to_text.convert(
    file=audio_data,
    model_id="scribe_v2", # Model to use
    # Entity types to detect, accepts a list of specific entity types or categories.
    # To detect all entity types, use the "all" category.
    entity_detection=["pii"],
)

print("Entities detected:", transcription.entities)

import { ElevenLabsClient } from "@elevenlabs/elevenlabs-js";
import "dotenv/config";

const elevenlabs = new ElevenLabsClient({
  apiKey: process.env.ELEVENLABS_API_KEY,
});

const response = await fetch(
  "https://storage.googleapis.com/eleven-public-cdn/documentation_assets/audio/stt-entity-detection-pii.mp3"
);
const audioBlob = new Blob([await response.arrayBuffer()], { type: "audio/mp3" });

const transcription = await elevenlabs.speechToText.convert({
  file: audioBlob,
  modelId: "scribe_v2", // Model to use
  // Entity types to detect, accepts a list of specific entity types or categories.
  // To detect all entity types, use the "all" category.
  entityDetection: ["pii"],
});

console.log("Entities detected:", transcription.entities);

transcription = elevenlabs.speech_to_text.convert(
    file=audio_file,
    model_id="scribe_v2",
    entity_detection=["pii"],
    entity_redaction=["pii"],
    entity_redaction_mode="enumerated_entity_type",
)

print(transcription.text)
# "Hi {NAME_0}, your card ending in {CREDIT_CARD_0} was declined."

const transcription = await elevenlabs.speechToText.convert({
  file: audioBlob,
  modelId: "scribe_v2",
  entityDetection: ["pii"],
  entityRedaction: ["pii"],
  entityRedactionMode: "enumerated_entity_type",
});

console.log(transcription.text);
// "Hi {NAME_0}, your card ending in {CREDIT_CARD_0} was declined."