ElevenLabs / Speech with character timings (for captions)

ElevenLabs tool elevenlabs-text-to-speech on looot: input fields, $0.00008 per result, output shape, and code to run it with curl, JavaScript or Python.

Reads text aloud and returns the speech (base64) plus the timing of every character, for captions and lip sync. Send text (up to 2,000 characters); voice_id, model_id and output_format are optional. For a plain MP3 download, use elevenlabs-text-to-speech-audio.

Tool id: elevenlabs-text-to-speech
Provider: ElevenLabs
Job: Turn text into speech with character timings (audio.speech.timestamps)
Price: $0.00008 per result. A call that fails at the provider costs $0.

Inputs

Name	Type	Required	Description
`language_code`	string	no	Optional ISO 639-1 language code, for example en or fr.
`model_id`	string	no	Voice model. eleven_multilingual_v2 and eleven_v3 cost $0.08 per 1,000 characters; eleven_flash_v2_5 and eleven_turbo_v2_5 cost $0.04. Defaults to eleven_multilingual_v2.
`text`	string	yes	The words to speak, up to 2,000 characters (about two minutes of speech).
`voice_settings`	object	no	Optional: stability, similarity_boost, style, use_speaker_boost, speed.
`output_format`	string	no	Audio format. Defaults to mp3_22050_32, which keeps long texts under the 1 MB reply limit.
`voice_id`	string	no	ElevenLabs voice id. Defaults to Rachel (21m00Tcm4TlvDq8ikWAM).

Output

Shape of the run’s result, the expected shape, not yet checked against real answers:

{ audio_base64: string, alignment: { characters: string[], character_start_times_seconds: number[], character_end_times_seconds: number[] } }

Run it

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":"elevenlabs-text-to-speech","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: "elevenlabs-text-to-speech",
    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": "elevenlabs-text-to-speech",
        "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:audio.speech.timestamps as endpointId; see the job page.