Redact PII from Text Using LLM Gateway

This guide will show you how to use AssemblyAI’s LLM Gateway to redact personally identifiable information (PII) from text.

Quickstart

Python
JavaScript

import requests
import time
import json
import re

base_url = "https://api.assemblyai.com"
headers = {"authorization": "<YOUR_API_KEY>"}

def generate_ner(transcript_text):
    prompt = '''
    You will be given a transcript of a conversation or text. Your task is to generate named entities from the given transcript text.

    Please identify and extract the following named entities from the transcript:

    1. Person names
    2. Organization names
    3. Email addresses
    4. Phone numbers
    5. Full addresses

    When extracting these entities, make sure to return the exact spelling and formatting as they appear in the transcript. Do not modify or standardize the entities in any way.

    Present your results in a JSON format with a single field named "named_entities". This field should contain an array of strings, where each string is a named entity you've identified. For example:
    {
      "named_entities": ["John Doe", "Acme Corp", "john.doe@example.com", "123-456-7890", "123 Main St, Anytown, USA 12345"]
    }

    Important: Do not include any other information, explanations, or text in your response. Your output should consist solely of the JSON object containing the named entities.

    If you do not find any named entities of a particular type, simply return an empty array for the "named_entities" field.
    '''

    llm_gateway_data = {
        "model": "claude-sonnet-4-6",
        "messages": [
            {"role": "user", "content": f"{prompt}\n\nTranscript: {transcript_text}"}
        ],
        "max_tokens": 1000,
        "temperature": 0.0
    }

    response = requests.post(
        "https://llm-gateway.assemblyai.com/v1/chat/completions",
        headers=headers,
        json=llm_gateway_data
    )

    result = response.json()["choices"][0]["message"]["content"]

    try:
        res_json = json.loads(result)
    except:
        res_json = {'named_entities': []}

    named_entities = res_json.get('named_entities', [])
    return named_entities

# Step 1: Transcribe audio
with open("./my-audio.mp3", "rb") as f:
    response = requests.post(base_url + "/v2/upload", headers=headers, data=f)

upload_url = response.json()["upload_url"]
data = {"audio_url": upload_url}

response = requests.post(base_url + "/v2/transcript", json=data, headers=headers)
transcript_id = response.json()['id']
polling_endpoint = base_url + "/v2/transcript/" + transcript_id

while True:
    transcription_result = requests.get(polling_endpoint, headers=headers).json()
    if transcription_result['status'] == 'completed':
        break
    elif transcription_result['status'] == 'error':
        raise RuntimeError(f"Transcription failed: {transcription_result['error']}")
    else:
        time.sleep(3)

# Step 2: Split transcript into sentences and redact PII
transcript_text = transcription_result['text']
sentences = re.split(r'[.!?]+', transcript_text)
redacted_transcript = ''

for sentence in sentences:
    sentence = sentence.strip()
    if not sentence:
        continue

    generated_entities = generate_ner(sentence)
    redacted_sentence = sentence

    for entity in generated_entities:
        redacted_sentence = redacted_sentence.replace(entity, '#' * len(entity))

    redacted_transcript += redacted_sentence + '. '
    print(redacted_sentence)

print('\nFull redacted transcript:')
print(redacted_transcript)

import fs from "fs-extra";

const baseUrl = "https://api.assemblyai.com";
const headers = { authorization: "<YOUR_API_KEY>" };

async function generateNer(transcriptText) {
  const prompt = `
    You will be given a transcript of a conversation or text. Your task is to generate named entities from the given transcript text.

    Please identify and extract the following named entities from the transcript:

    1. Person names
    2. Organization names
    3. Email addresses
    4. Phone numbers
    5. Full addresses

    When extracting these entities, make sure to return the exact spelling and formatting as they appear in the transcript. Do not modify or standardize the entities in any way.

    Present your results in a JSON format with a single field named "named_entities". This field should contain an array of strings, where each string is a named entity you've identified. For example:
    {
      "named_entities": ["John Doe", "Acme Corp", "john.doe@example.com", "123-456-7890", "123 Main St, Anytown, USA 12345"]
    }

    Important: Do not include any other information, explanations, or text in your response. Your output should consist solely of the JSON object containing the named entities.

    If you do not find any named entities of a particular type, simply return an empty array for the "named_entities" field.
    `;

  const llmGatewayData = {
    model: "claude-sonnet-4-6",
    messages: [
      { role: "user", content: `${prompt}\n\nTranscript: ${transcriptText}` },
    ],
    max_tokens: 1000,
    temperature: 0.0,
  };

  let res = await fetch("https://llm-gateway.assemblyai.com/v1/chat/completions", {
    method: "POST",
    headers: { ...headers, "Content-Type": "application/json" },
    body: JSON.stringify(llmGatewayData),
  });
  if (!res.ok) throw new Error(`Error: ${res.status}`);
  const response = await res.json();

  const result = response.choices[0].message.content;

  let resJson;
  try {
    resJson = JSON.parse(result);
  } catch (e) {
    resJson = { named_entities: [] };
  }

  const namedEntities = resJson.named_entities || [];
  return namedEntities;
}

// Step 1: Transcribe audio
const fileData = await fs.readFile("./my-audio.mp3");
let res = await fetch(baseUrl + "/v2/upload", {
  method: "POST",
  headers,
  body: fileData,
});
if (!res.ok) throw new Error(`Error: ${res.status}`);
const uploadResponse = await res.json();

const uploadUrl = uploadResponse.upload_url;
const data = { audio_url: uploadUrl };

res = await fetch(baseUrl + "/v2/transcript", {
  method: "POST",
  headers: { ...headers, "Content-Type": "application/json" },
  body: JSON.stringify(data),
});
if (!res.ok) throw new Error(`Error: ${res.status}`);
const transcriptResponse = await res.json();
const transcriptId = transcriptResponse.id;
const pollingEndpoint = baseUrl + "/v2/transcript/" + transcriptId;

let transcriptionResult;
while (true) {
  res = await fetch(pollingEndpoint, { headers });
  if (!res.ok) throw new Error(`Error: ${res.status}`);
  transcriptionResult = await res.json();
  if (transcriptionResult.status === "completed") {
    break;
  } else if (transcriptionResult.status === "error") {
    throw new Error(`Transcription failed: ${transcriptionResult.error}`);
  } else {
    await new Promise((resolve) => setTimeout(resolve, 3000));
  }
}

// Step 2: Split transcript into sentences and redact PII
const transcriptText = transcriptionResult.text;
const sentences = transcriptText.split(/[.!?]+/);
let redactedTranscript = "";

for (let sentence of sentences) {
  sentence = sentence.trim();
  if (!sentence) continue;

  const generatedEntities = await generateNer(sentence);
  let redactedSentence = sentence;

  for (const entity of generatedEntities) {
    redactedSentence = redactedSentence.replaceAll(entity, "#".repeat(entity.length));
  }

  redactedTranscript += redactedSentence + ". ";
  console.log(redactedSentence);
}

console.log("\nFull redacted transcript:");
console.log(redactedTranscript);

Get Started

Before we begin, make sure you have an AssemblyAI account and an API key. You can sign up for an account and get your API key from your dashboard.

Step-by-Step Instructions

Install dependencies

Install the required packages:

Python
JavaScript

pip install requests

npm install fs-extra

Import the required packages and set up your API client:

Python
JavaScript

import requests
import time
import json
import re

base_url = "https://api.assemblyai.com"
headers = {"authorization": "<YOUR_API_KEY>"}

import fs from "fs-extra";

const baseUrl = "https://api.assemblyai.com";
const headers = { authorization: "<YOUR_API_KEY>" };

Python
JavaScript

Define a function generate_ner that uses LLM Gateway to identify named entities (person names, organizations, emails, phone numbers, addresses) in a given text.

def generate_ner(transcript_text):
    prompt = '''
    You will be given a transcript of a conversation or text. Your task is to generate named entities from the given transcript text.

    Please identify and extract the following named entities from the transcript:

    1. Person names
    2. Organization names
    3. Email addresses
    4. Phone numbers
    5. Full addresses

    When extracting these entities, make sure to return the exact spelling and formatting as they appear in the transcript. Do not modify or standardize the entities in any way.

    Present your results in a JSON format with a single field named "named_entities". This field should contain an array of strings, where each string is a named entity you've identified. For example:
    {
      "named_entities": ["John Doe", "Acme Corp", "john.doe@example.com", "123-456-7890", "123 Main St, Anytown, USA 12345"]
    }

    Important: Do not include any other information, explanations, or text in your response. Your output should consist solely of the JSON object containing the named entities.

    If you do not find any named entities of a particular type, simply return an empty array for the "named_entities" field.
    '''

    llm_gateway_data = {
        "model": "claude-sonnet-4-6",
        "messages": [
            {"role": "user", "content": f"{prompt}\n\nTranscript: {transcript_text}"}
        ],
        "max_tokens": 1000,
        "temperature": 0.0
    }

    response = requests.post(
        "https://llm-gateway.assemblyai.com/v1/chat/completions",
        headers=headers,
        json=llm_gateway_data
    )

    result = response.json()["choices"][0]["message"]["content"]

    try:
        res_json = json.loads(result)
    except:
        res_json = {'named_entities': []}

    named_entities = res_json.get('named_entities', [])
    return named_entities

Define a function generateNer that uses LLM Gateway to identify named entities (person names, organizations, emails, phone numbers, addresses) in a given text.

async function generateNer(transcriptText) {
  const prompt = `
    You will be given a transcript of a conversation or text. Your task is to generate named entities from the given transcript text.

    Please identify and extract the following named entities from the transcript:

    1. Person names
    2. Organization names
    3. Email addresses
    4. Phone numbers
    5. Full addresses

    When extracting these entities, make sure to return the exact spelling and formatting as they appear in the transcript. Do not modify or standardize the entities in any way.

    Present your results in a JSON format with a single field named "named_entities". This field should contain an array of strings, where each string is a named entity you've identified. For example:
    {
      "named_entities": ["John Doe", "Acme Corp", "john.doe@example.com", "123-456-7890", "123 Main St, Anytown, USA 12345"]
    }

    Important: Do not include any other information, explanations, or text in your response. Your output should consist solely of the JSON object containing the named entities.

    If you do not find any named entities of a particular type, simply return an empty array for the "named_entities" field.
    `;

  const llmGatewayData = {
    model: "claude-sonnet-4-6",
    messages: [
      { role: "user", content: `${prompt}\n\nTranscript: ${transcriptText}` },
    ],
    max_tokens: 1000,
    temperature: 0.0,
  };

  let res = await fetch("https://llm-gateway.assemblyai.com/v1/chat/completions", {
    method: "POST",
    headers: { ...headers, "Content-Type": "application/json" },
    body: JSON.stringify(llmGatewayData),
  });
  if (!res.ok) throw new Error(`Error: ${res.status}`);
  const response = await res.json();

  const result = response.choices[0].message.content;

  let resJson;
  try {
    resJson = JSON.parse(result);
  } catch (e) {
    resJson = { named_entities: [] };
  }

  const namedEntities = resJson.named_entities || [];
  return namedEntities;
}

Transcribe an audio file using the AssemblyAI API:

Python
JavaScript

with open("./my-audio.mp3", "rb") as f:
    response = requests.post(base_url + "/v2/upload", headers=headers, data=f)

upload_url = response.json()["upload_url"]
data = {"audio_url": upload_url}  # You can also use a URL to an audio or video file on the web

response = requests.post(base_url + "/v2/transcript", json=data, headers=headers)
transcript_id = response.json()['id']
polling_endpoint = base_url + "/v2/transcript/" + transcript_id

while True:
    transcription_result = requests.get(polling_endpoint, headers=headers).json()
    if transcription_result['status'] == 'completed':
        break
    elif transcription_result['status'] == 'error':
        raise RuntimeError(f"Transcription failed: {transcription_result['error']}")
    else:
        time.sleep(3)

const fileData = await fs.readFile("./my-audio.mp3");
let res = await fetch(baseUrl + "/v2/upload", {
  method: "POST",
  headers,
  body: fileData,
});
if (!res.ok) throw new Error(`Error: ${res.status}`);
const uploadResponse = await res.json();

const uploadUrl = uploadResponse.upload_url;
const data = { audio_url: uploadUrl }; // You can also use a URL to an audio or video file on the web

res = await fetch(baseUrl + "/v2/transcript", {
  method: "POST",
  headers: { ...headers, "Content-Type": "application/json" },
  body: JSON.stringify(data),
});
if (!res.ok) throw new Error(`Error: ${res.status}`);
const transcriptResponse = await res.json();
const transcriptId = transcriptResponse.id;
const pollingEndpoint = baseUrl + "/v2/transcript/" + transcriptId;

let transcriptionResult;
while (true) {
  res = await fetch(pollingEndpoint, { headers });
  if (!res.ok) throw new Error(`Error: ${res.status}`);
  transcriptionResult = await res.json();
  if (transcriptionResult.status === "completed") {
    break;
  } else if (transcriptionResult.status === "error") {
    throw new Error(`Transcription failed: ${transcriptionResult.error}`);
  } else {
    await new Promise((resolve) => setTimeout(resolve, 3000));
  }
}

Python
JavaScript

Split the transcript into sentences, identify named entities using generate_ner, and replace them with # characters:

transcript_text = transcription_result['text']
sentences = re.split(r'[.!?]+', transcript_text)
redacted_transcript = ''

for sentence in sentences:
    sentence = sentence.strip()
    if not sentence:
        continue

    generated_entities = generate_ner(sentence)
    redacted_sentence = sentence

    for entity in generated_entities:
        redacted_sentence = redacted_sentence.replace(entity, '#' * len(entity))

    redacted_transcript += redacted_sentence + '. '
    print(redacted_sentence)

Split the transcript into sentences, identify named entities using generateNer, and replace them with # characters:

const transcriptText = transcriptionResult.text;
const sentences = transcriptText.split(/[.!?]+/);
let redactedTranscript = "";

for (let sentence of sentences) {
  sentence = sentence.trim();
  if (!sentence) continue;

  const generatedEntities = await generateNer(sentence);
  let redactedSentence = sentence;

  for (const entity of generatedEntities) {
    redactedSentence = redactedSentence.replaceAll(entity, "#".repeat(entity.length));
  }

  redactedTranscript += redactedSentence + ". ";
  console.log(redactedSentence);
}

Print the fully redacted transcript:

Python
JavaScript

print('\nFull redacted transcript:')
print(redacted_transcript)

console.log("\nFull redacted transcript:");
console.log(redactedTranscript);

Getting started

Features

API reference

Core concepts

Voice AI Guides

Redact PII from Text Using LLM Gateway

Quickstart

Get Started

Step-by-Step Instructions

Install dependencies

​Quickstart

​Get Started

​Step-by-Step Instructions

​Install dependencies

Quickstart

Get Started

Step-by-Step Instructions

Install dependencies