Speech to text

parakeet-tdt-0.6b-v2

NVIDIA Parakeet English TDT.

Native waveform: Word timestamps. English.. Live price and availability are on GET /v1/models/parakeet-tdt-0.6b-v2.

Parameters

FieldTypeDescription
params.response_format
Default verbose_json
stringjson returns the transcript in result.text. verbose_json also returns language, duration, segments, and words. When this field is omitted, the API sets verbose_json.
params.timestamp_granularity
Default word
stringnone or word. none omits timing. word returns a time range per word. Omitting the field, or sending null, uses word. word fills response_format to verbose_json when that field is omitted.
params.blank_penalty
Default 0
number0 to 5. Step 0.01.

Example

curl https://api.pascalai.co/v1/speech-to-text \
  -H "Authorization: Bearer $PASCAL_API_KEY" \
  -H "Idempotency-Key: $(uuidgen)" \
  -F model=parakeet-tdt-0.6b-v2 \
  -F params='{"response_format":"verbose_json","timestamp_granularity":"word"}' \
  -F file=@input.wav

curl https://api.pascalai.co/v1/speech-to-text/$JOB_ID \
  -H "Authorization: Bearer $PASCAL_API_KEY"