`sarvam-saaras`

Saaras v4. $0.005 / min. Diarization is $0.0075 / min. language and language_code are the same field.

The call is Pascal’s. Send Authorization: Bearer with a Pascal key, and Pascal’s body: model, the file or the text, and params. Inside params, a Pascal name and the provider’s own name are both accepted. If both are sent and they disagree, the request is rejected. The provider’s SDK and host are not this API. The API request fee is not charged. A studio call needs a Creator plan or an API balance.

Native waveform: File upload. language unknown detects the language. Odia is od or or. Both are the same.. Live price and availability are on GET /v1/models/sarvam-saaras.

Files longer than about 30 seconds, and any diarized file, run as a batch job.
Audio must be 2 hours or less.

Parameters

Field	Type	Description
`params.language` Default unknown	string	unknown detects the language. A short code or Sarvam’s code: en or en-IN, hi or hi-IN, bn or bn-IN, gu or gu-IN, kn or kn-IN, ml or ml-IN, mr or mr-IN, pa or pa-IN, ta or ta-IN, te or te-IN. Odia is od or or. Both are the same, and speech stores od-IN. language_code is the same field. saaras:v3 also accepts as, ur, ne, kok, ks, sd, sa, sat, mni, brx, mai, and doi.
`params.mode` Default transcribe	string	transcribe, translate, verbatim, translit, or codemix.
`params.diarize` Default false	boolean	Speaker diarization. speaker_diarization and with_diarization are the same field. Diarization uses the batch job and the higher rate.
`params.custom_terms`	string or array	Up to 50 terms, 64 characters each. keyterms is the same field.
`params.with_timestamps` Default false	boolean	Include chunk timestamps.

Example

curl https://api.pascalai.co/v1/speech-to-text \
  -H "Authorization: Bearer $PASCAL_API_KEY" \
  -H "Idempotency-Key: $(uuidgen)" \
  -F model=sarvam-saaras \
  -F params='{"language":"hi-IN","mode":"transcribe"}' \
  -F file=@input.wav

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