Formatting & Redaction

Custom Keyword Redaction

Masks specific words or phrases using regex (case-insensitive, no LLM). Works independently of enable_profanity_hashing.

Python SDK

python
config = TranscriptionConfig(
    model="zero-indic",
    hash_keywords=["account number", "card number", "OTP"],
)
result = await client.asr.transcribe("audio.wav", config=config)

print(result.text)
# aapka **** 4321 hai aur aapka **** kal bheja gaya tha
for seg in result.segments:
    print(seg.text)
# aapka **** 4321 hai aur aapka **** kal bheja gaya tha

REST API

terminal
curl -X POST https://asr.shunyalabs.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer <API_KEY>" \
  -F "[email protected]" \
  -F "model=zero-indic" \
  -F 'hash_keywords=["account number", "card number", "OTP"]'

Output

json
{
  "text": "aapka **** 4321 hai aur aapka **** kal bheja gaya tha",
  "segments": [
    { "start": 0.0, "end": 5.0, "text": "aapka **** 4321 hai aur aapka **** kal bheja gaya tha" }
  ]
}
PreviousProfanity HashingNext Supported Formats