Features
PII Redaction and Profanity Filtering
Strip personal information or mask profanity in the transcript output with two request flags.
Two independent flags clean the transcript output at processing time, before the text is ever stored on the transcript:
| Flag | Effect |
|---|---|
| pii_redaction | Detects personally identifiable information (such as names, phone numbers, addresses, and account numbers) and replaces it in the returned text and words. |
| profanity_filter | Masks profanity in the returned text and words. |
Quickstart
curl -s -X POST https://api.realtimevoicekit.com/v2/transcripts \
-H "Authorization: Bearer rtvk_your_api_key" \
-H "Content-Type: application/json" \
-d '{
"audio_url": "https://example.com/support-call.mp3",
"pii_redaction": true,
"profanity_filter": true
}'Notes
- Redaction and filtering are decided at create time; they cannot be applied to an already completed transcript. Re-run the file with the flags set instead.
- Redacted content is replaced in the stored transcript, so downstream exports such as subtitles and word search operate on the cleaned text.
- The audio file itself is not modified; only the transcript output is.