`deepgram-aura-2`

Aura-2 speech. $30 per million characters. Every published Aura-2 voice.

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: Voice ids look like aura-2-thalia-en. model and voice are the same field.. Live price and availability are on GET /v1/models/deepgram-aura-2.

Spanish, German, French, Dutch, Italian, Japanese, and English voices are all accepted.
If model and voice are both sent and they disagree, the request is rejected.

Parameters

Field	Type	Description
`params.model` Default aura-2-thalia-en	string	Aura-2 voice id. voice is the same field.
`params.encoding`	string	Omit to use Deepgram’s default. linear16, mp3, opus, flac, aac, mulaw, or alaw where that voice allows it.
`params.container`	string	Container for a compressed encoding.
`params.sample_rate`	integer	Sample rate for raw encodings.
`params.speed`	number	Speaking rate.

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": "deepgram-aura-2",
  "text": "Hello from Pascal.",
  "params": {
    "model": "aura-2-thalia-en"
  }
}'

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