API Get key

ElevenLabsAudio

Voiceover

Voiceover from your script with ElevenLabs, with word timings for captions.

Price
5 crper take · varies with length or size
Usual time
≈ 20 s
Model id
audio.tts

Playground

Playground

Voice model
More settings

0.7 - 1.2

0 - 1

Sign up to run it

Change the settings: the price and the code follow. You need an account to run it.

audio.tts
Voices
66
Languages
7
Takes
Text

No example of this model yet. These are its real settings.

# 1. Create the job. It is charged once and refunded if it fails.
JOB_ID=$(curl -s -X POST https://staglight.ai/api/v1/jobs \
  -H "Authorization: Bearer $STAGLIGHT_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "op": "audio.tts",
    "params": {
      "text": "A premium product shot of a glass serum bottle on wet stone, soft window light"
    }
  }' | jq -r .id)

# 2. Poll until it finishes. Each call waits up to 30 seconds.
while :; do
  JOB=$(curl -s "https://staglight.ai/api/v1/jobs/$JOB_ID?wait=30" -H "Authorization: Bearer $STAGLIGHT_API_KEY")
  case "$(echo "$JOB" | jq -r .status)" in queued|running) ;; *) break ;; esac
done

# 3. Download the result from outputs[0].download_url.
DOWNLOAD_URL=$(echo "$JOB" | jq -r '.outputs[0].download_url')
curl -L -o result.mp3 "$DOWNLOAD_URL"
import os, uuid, requests

BASE = "https://staglight.ai/api/v1"
HEADERS = {"Authorization": f"Bearer {os.environ['STAGLIGHT_API_KEY']}"}

# 1. Create the job. It is charged once and refunded if it fails.
r = requests.post(f"{BASE}/jobs", timeout=60,
                  headers={**HEADERS, "Idempotency-Key": str(uuid.uuid4())},
                  json={
                    "op": "audio.tts",
                    "params": {
                      "text": "A premium product shot of a glass serum bottle on wet stone, soft window light"
                    }
                  })
r.raise_for_status()
job = r.json()

# 2. Poll until it finishes. Each call waits up to 30 seconds.
while job["status"] in ("queued", "running"):
    job = requests.get(f"{BASE}/jobs/{job['id']}", headers=HEADERS,
                       params={"wait": 30}, timeout=60).json()

# 3. Download the result from outputs[0].download_url.
print(job["outputs"][0]["download_url"] if job["outputs"] else job["data"] or job["error"])
// Node 18 or newer. Save as run.mjs: top-level await needs a module.
const BASE = "https://staglight.ai/api/v1";
const headers = { Authorization: `Bearer ${process.env.STAGLIGHT_API_KEY}` };

// 1. Create the job. It is charged once and refunded if it fails.
let res = await fetch(`${BASE}/jobs`, {
  method: "POST",
  headers: { ...headers, "Content-Type": "application/json", "Idempotency-Key": crypto.randomUUID() },
  body: JSON.stringify({
    "op": "audio.tts",
    "params": {
      "text": "A premium product shot of a glass serum bottle on wet stone, soft window light"
    }
  }),
});
if (!res.ok) throw new Error((await res.json()).error.message);
let job = await res.json();

// 2. Poll until it finishes. Each call waits up to 30 seconds.
while (job.status === "queued" || job.status === "running") {
  job = await (await fetch(`${BASE}/jobs/${job.id}?wait=30`, { headers })).json();
}

// 3. Download the result from outputs[0].download_url.
console.log(job.outputs[0]?.download_url ?? job.data ?? job.error);
{
  "id": "job_19a2b3c4d5e6f7a8b9c0d1",
  "op": "audio.tts",
  "status": "queued",
  "credits": 5,
  "title": "",
  "params": {
    "text": "A premium product shot of a glass serum bottle on wet stone, soft window light"
  },
  "progress": null,
  "outputs": [],
  "data": null,
  "error": null,
  "run_id": null,
  "source": "api",
  "created_at": "2026-11-06T12:00:00Z",
  "finished_at": null,
  "eta_seconds": 20
}

What it costs

Voice modelPrice
multilingual-v25 cr
turbo-2.53 cr

These prices are at a default length: the price follows the length of your text or file, and the exact price shows before the job runs. The playground shows the exact price for your settings. A job is charged once when it is accepted, and refunded if it fails.

Parameters

NameTypeDefaultAllowed
textrequiredScript text string Up to 5,000 characters
voiceVoice enum hpp4J3VqNfWAUOO0d1Us hpp4J3VqNfWAUOO0d1Us, EkK5I93UQWFDigLMpZcX, Z3R5wn05IrDiVCyEkUrK, NNl6r8mD7vthiJatiJt1, YOq2y2Up4RgXP2HyXjE5, B8gJV1IhpuegLxdpXFOE, 2zRM7PkgwBPiau2jvVXc, 1SM7GgM6IMuvQlz2BwM3, 5l5f8iK3YPeGga21rQIX, scOwDtmlUjD3prqpp97I, NOpBlnGInO9m6vDvFkFC, BZgkqPqms7Kj9ulSkVzn, ...
modelVoice model enum multilingual-v2 multilingual-v2, turbo-2.5
languageLanguage enum auto auto, es, en, pt, fr, it, de
speedSpeed number 1.0 0.7 - 1.2
stabilityStability number 0.5 0 - 1
previous_textPrevious text string Up to 5,000 characters
next_textNext text string Up to 5,000 characters
allow_fallbackBackup voice if ElevenLabs fails boolean true

Send these inside params. Files are media ids from POST /api/v1/uploads. View documentation

More models