Skip to content

Commit

Permalink
fix: add JSON response, fix code examples, and other minor adjustment…
Browse files Browse the repository at this point in the history 
…s for pii redaction page
  • Loading branch information
@a-dinoto
a-dinoto committed Feb 6, 2025
1 parent 19bb734 commit 146b509
Showing 1 changed file with 56 additions and 83 deletions.
139 changes: 56 additions & 83 deletions fern/pages/03-audio-intelligence/pii-redaction.mdx
View file
Original file line number Diff line number Diff line change
Expand Up @@ -139,13 +139,19 @@ func main() {
</Tab>
<Tab value="java" title="Java">

Enable PII Redaction by setting `redact_pii` to `true` in the transcription
Enable PII Redaction by setting `redactPii` to `true` in the transcription
config.

Use `redact_pii_policies` to specify the information you want to
Use `redactPiiPolicies` to specify the information you want to
redact. For the full list of policies, see [PII policies](#pii-policies).

```java {15-17}public final class App {
```java {15-17}

import com.assemblyai.api.AssemblyAI;
import com.assemblyai.api.resources.transcripts.types.*;
import java.util.List;

public final class App {
public static void main(String[] args) {
AssemblyAI client = AssemblyAI.builder()
.apiKey("<YOUR_API_KEY>")
Expand Down Expand Up @@ -254,43 +260,12 @@ getting hit in the US. Is because there's a couple of weather systems that ...

In addition to redacting sensitive information from the transcription text, you can also generate a version of the original audio file with the PII "beeped" out.

<Tabs>

<Tab title="Python">

To create a redacted version of the audio file, use the `set_redact_pii()`
method on the `TranscriptionConfig` with `redact_audio` to `True`.

Use `get_redacted_audio_url()` on the transcript to get the URL to the redacted audio file.

</Tab>
<Tab title="TypeScript">

To create a redacted version of the audio file, set `redact_pii_audio` to
`true` in the transcription config. Use `redact_pii_audio_quality` to specify
the quality of the redacted audio file.

</Tab>
<Tab title="Go">

To create a redacted version of the audio file, set `RedactPIIAudio` to
`true` in the transcription config. Use `RedactPIIAudioQuality` to specify
the quality of the redacted audio file.

</Tab>
<Tab title="C#">

To create a redacted version of the audio file, set `RedactPiiAudio` to
`true` in the transcription config. Use `RedactPiiAudioQuality` to specify
the quality of the redacted audio file.

</Tab>

</Tabs>

<Tabs groupId="language">
<Tab value="python" title="Python" default>
To create a redacted version of the audio file, use the `set_redact_pii()`
method on the `TranscriptionConfig` with `redact_audio` to `True`.

Use `get_redacted_audio_url()` on the transcript to get the URL to the redacted audio file.
```python {7,12}
config = aai.TranscriptionConfig().set_redact_pii(
policies=[
Expand All @@ -309,7 +284,11 @@ print(transcript.get_redacted_audio_url())
</Tab>
<Tab value="typescript" title="TypeScript">

```ts {5-6,11}
To create a redacted version of the audio file, set `redact_pii_audio` to
`true` in the transcription config. Use `redact_pii_audio_quality` to specify
the quality of the redacted audio file.

```ts {5-6}
const params: TranscribeParams = {
audio: audioUrl,
redact_pii: true,
Expand All @@ -330,10 +309,24 @@ const run = async () => {

run()
```
You can also retrieve the redacted audio file itself using `redactedAudioFile()`.
The following code writes the redacted audio file to a local file, using `writeFile()` from Node.js.

```typescript
import fs from "fs/promises";

...

const audioFile = await client.transcripts.redactedAudioFile(transcript.id);
await fs.writeFile('./redacted-audio.wav', audioFile.body!, 'binary');
```
</Tab>
<Tab value="golang" title="Go">

To create a redacted version of the audio file, set `RedactPIIAudio` to
`true` in the transcription config. Use `RedactPIIAudioQuality` to specify
the quality of the redacted audio file.

```go {5-6}
transcript, _ := client.Transcripts.TranscribeFromURL(ctx, audioURL, &aai.TranscriptOptionalParams{
RedactPII: aai.Bool(true),
Expand All @@ -350,6 +343,9 @@ fmt.Printf("Status: %s, Redacted audio URL: %s", resp.Status, aai.ToString(resp.

</Tab>
<Tab value="java" title="Java">

To create a redacted version of the audio file, set `redactPiiAudio` to `true` in the transcription config. Use `redactPiiAudioQuality` to specify
the quality of the redacted audio file.

```java {4-5}
var params = TranscriptOptionalParams.builder()
Expand All @@ -369,6 +365,10 @@ System.out.println("Status: " + redactionResult.getStatus() + ", Redacted audio
</Tab>
<Tab value="csharp" title="C#">

To create a redacted version of the audio file, set `RedactPiiAudio` to
`true` in the transcription config. Use `RedactPiiAudioQuality` to specify
the quality of the redacted audio file.

```csharp {13-14}
using AssemblyAI;
using AssemblyAI.Transcripts;
Expand All @@ -390,11 +390,22 @@ var redactionResult = await client.Transcripts.GetRedactedAudioAsync(transcript.

Console.WriteLine($"Status: {redactionResult.Status}, " +
$"Redacted audio URL: {redactionResult.RedactedAudioUrl}");
```
You can also retrieve the redacted audio file as a stream using the `GetRedactedAudioFileAsync` method.
The following code stores the redacted audio file locally as `redacted-audio.wav`.

```csharp
await using var redactedAudioFileStream = await client.Transcripts.GetRedactedAudioFileAsync(transcript.Id);
await using var fileStream = File.OpenWrite("./redacted_audio.wav");
redactedAudioFileStream.CopyTo(fileStream);
```

</Tab>
<Tab value="ruby" title="Ruby">

To create a redacted version of the audio file, set `redact_pii_audio` to `true` in the transcription config. Use `redact_pii_audio_quality` to specify
the quality of the redacted audio file.

```ruby {9-11}
transcript = client.transcripts.transcribe(
audio_url: audio_url,
Expand All @@ -420,36 +431,6 @@ printf(
</Tab>
</Tabs>

<Tabs>
<Tab title="TypeScript">

You can also retrieve the redacted audio file itself using `redactedAudioFile()`.
The following code writes the redacted audio file to a local file, using `writeFile()` from Node.js.

```typescript


...

const audioFile = await client.transcripts.redactedAudioFile(transcript.id);
await fs.writeFile('./redacted-audio.wav', audioFile.body!, 'binary');
```

</Tab>
<Tab title="Python">

You can also retrieve the redacted audio file as a stream using the `GetRedactedAudioFileAsync` method.
The following code stores the redacted audio file locally as `redacted-audio.wav`.

```csharp
await using var redactedAudioFileStream = await client.Transcripts.GetRedactedAudioFileAsync(transcript.Id);
await using var fileStream = File.OpenWrite("./redacted_audio.wav");
redactedAudioFileStream.CopyTo(fileStream);
```

</Tab>
</Tabs>

<Note title="Supported languages">

You can only create redacted audio files for transcriptions in English and Spanish.
Expand Down Expand Up @@ -498,15 +479,7 @@ curl https://api.assemblyai.com/v2/transcript \

### Response

<CodeBlock>
<JsonViewer
displayDataTypes={false}
quotesOnKeys={false}
displayObjectSize={false}
collapsed={2}
src={(({ text }) => ({ text }))(piiRedaction)}
/>
</CodeBlock>
<EndpointResponseSnippet endpoint='GET /v2/transcript/{transcript_id}' />

| Key | Type | Description |
| ------ | ------ | ----------------------------- |
Expand All @@ -529,12 +502,12 @@ The response also includes the request parameters used to generate the transcrip
| `credit_card_expiration` | Expiration date of a credit card | |
| `credit_card_number` | Credit card number | |
| `date` | Specific calendar date | December 18 |
| `date_of_birth` | Date of birth | Date of Birth: March 7,1961 |
| `drivers_license` | Driver's license number. | DL# 356933-540 |
| `date_of_birth` | Date of birth | Date of Birth: March 7, 1961 |
| `drivers_license` | Driver's license number | DL# 356933-540 |
| `drug` | Medications, vitamins, or supplements | Advil, Acetaminophen, Panadol |
| `email_address` | Email address | [email protected] |
| `event` | Name of an event or holiday | Olympics, Yom Kippur |
| `gender_sexuality` | Terms indicating gender identity or sexual orientation, including slang terms | female; bisexual; trans |
| `gender_sexuality` | Terms indicating gender identity or sexual orientation, including slang terms | female, bisexual, trans |
| `healthcare_number` | Healthcare numbers and health plan beneficiary numbers | Policy No.: 5584-486-674-YM |
| `injury` | Bodily injury | I broke my arm, I have a sprained wrist |
| `ip_address` | Internet IP address, including IPv4 and IPv6 formats | 192.168.0.1 |
Expand All @@ -547,7 +520,7 @@ The response also includes the request parameters used to generate the transcrip
| `number_sequence` | Numerical PII (including alphanumeric strings) that doesn't fall under other categories | |
| `occupation` | Job title or profession | professor, actors, engineer, CPA |
| `organization` | Name of an organization | CNN, McDonalds, University of Alaska, Northwest General Hospital |
| `passport_number` | Passport numbers, issued by any country | PA4568332; NU3C6L86S12 |
| `passport_number` | Passport numbers, issued by any country | PA4568332, NU3C6L86S12 |
| `password` | Account passwords, PINs, access keys, or verification answers | 27%alfalfa, temp1234, My mother's maiden name is Smith |
| `person_age` | Number associated with an age | 27, 75 |
| `person_name` | Name of a person | Bob, Doug Jones, Dr. Kay Martinez, MD |
Expand All @@ -557,7 +530,7 @@ The response also includes the request parameters used to generate the transcrip
| `url` | Internet addresses | https://www.assemblyai.com/ |
| `us_social_security_number` | Social Security Number or equivalent | |
| `username` | Usernames, login names, or handles | @AssemblyAI |
| `vehicle_id` | Vehicle identification numbers (VINs), vehicle serial numbers, and license plate numbers | 5FNRL38918B111818; BIF7547 |
| `vehicle_id` | Vehicle identification numbers (VINs), vehicle serial numbers, and license plate numbers | 5FNRL38918B111818, BIF7547 |



Expand All @@ -570,7 +543,7 @@ The response also includes the request parameters used to generate the transcrip
theme="dark"
iconColor="white"
>
Make sure that at least one <a href="#pii-policies">PII policy</a> has been
Make sure that at least one [PII policy](#pii-policies) has been
specified in your request, using the `redact_pii_policies`{' '}
parameter. If you're still experiencing issues, please reach out to our
support team for assistance.
Expand Down

0 comments on commit 146b509

Please sign in to comment.