`sarvam-bulbul`

Bulbul v3. $30 per million characters.

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: JSON text. Default speaker shubh. Default language en-IN.. Live price and availability are on GET /v1/models/sarvam-bulbul.

At most 2500 characters.
pitch and loudness are Bulbul v2 only.
Language defaults to English (India). This model does not detect it. en-IN is that same default.

Parameters

Field	Type	Description
`params.language` Default en-IN	string	This model does not detect the language. Omitted uses English (India). en or en-IN is that same default. Also 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 Bulbul stores od-IN. language_code is the same field.
`params.speaker` Default shubh	string	A published Bulbul speaker. voice is the same field.
`params.pace`	number	0.5 to 2.

Example

curl https://api.pascalai.co/v1/text-to-speech \
  -H "Authorization: Bearer $PASCAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "sarvam-bulbul",
  "text": "Keep walking toward the river.",
  "params": {
    "language": "en-IN",
    "speaker": "shubh",
    "output_format": "wav",
    "output_sample_rate": "source",
    "output_channels": "source"
  }
}'

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