Deepgram / Text to speech

Deepgram tool deepgram-speak on looot: input fields, $0.00003 per result, output shape, and code to run it with curl, JavaScript or Python.

Turns text (up to 1,000 characters) into spoken audio with a Deepgram Aura voice and returns it as an MP3 download (media.downloadPath).

Tool id: deepgram-speak
Provider: Deepgram
Job: Get speak (speak.get)
Price: $0.00003 per result. A call that fails at the provider costs $0.

Inputs

Name	Type	Required	Description
`text`	string	yes	The text content to be converted to speech Up to 1,000 characters.
`bit_rate`	string	no
`container`	string	no
`encoding`	string	no
`mip_opt_out`	boolean	no
`model`	string	no	Deepgram Aura voice, for example aura-2-thalia-en. Only aura-2-* and aura-* voices are allowed.
`sample_rate`	string	no
`speed`	number	no
`tag`	string	no

Output

The run’s result holds the provider’s answer. Signed in, looot inspect deepgram-speak prints its fields.

Every call needs your API token in LOOOT_TOKEN; Sign in shows how to get one. Each run also needs a new idempotency key, so a retry never pays twice. With wait: 30 the answer comes back inline when the run ends within 30 seconds. Otherwise you get the running run back: poll GET /v1/runs/<runId>.

Example input with placeholder values:

curl -X POST "https://api.looot.ai/v1/runs" \
  -H "Authorization: Bearer $LOOOT_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{"endpointId":"deepgram-speak","input":{"text":"<text>"},"wait":30}'

const response = await fetch("https://api.looot.ai/v1/runs", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.LOOOT_TOKEN}`,
    "Content-Type": "application/json",
    "Idempotency-Key": crypto.randomUUID(),
  },
  body: JSON.stringify({
    endpointId: "deepgram-speak",
    input: {
      text: "<text>",
    },
    wait: 30,
  }),
});
const run = await response.json();
console.log(run.status, run.result);

import os
import uuid

import requests

response = requests.post(
    "https://api.looot.ai/v1/runs",
    headers={
        "Authorization": f"Bearer {os.environ['LOOOT_TOKEN']}",
        "Idempotency-Key": str(uuid.uuid4()),
    },
    json={
        "endpointId": "deepgram-speak",
        "input": {
            "text": "<text>",
        },
        "wait": 30,
    },
    timeout=90,
)
run = response.json()
print(run["status"], run.get("result"))

To let looot pick among every provider of this job instead, send job:speak.get as endpointId; see the job page.

Deepgram / Text to speech

Inputs

Output

Run it