Eleven V4 Text-to-Speech converts text into expressive multilingual speech with configurable voice selection, stability, and similarity controls for narration, dialogue, localization, virtual assistants, and voice production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.08per run·~12 / $1
Eleven V4 converts text into expressive, natural-sounding speech for narration, voiceovers, and character performances. Choose a preset or custom voice, guide delivery with inline audio tags, and adjust voice stability and similarity to shape the final performance.
It is suited to high-quality spoken content where expressive delivery, multilingual speech, and voice consistency matter more than the lower-latency focus of the Turbo variant.
Expressive text-to-speech
Generate natural-sounding speech for narration, dialogue, and performance-driven content.
Audio-tag control
Guide delivery with inline cues such as [whispering] and [laughing].
Preset and custom voices
Choose a suggested voice or provide a custom voice_id.
Multilingual speech
Generate spoken content across multiple languages.
Voice controls
Adjust stability and similarity to tune delivery consistency and resemblance to the selected voice.
MP3 output
Receive the generated speech as a downloadable audio file.
| Parameter | Required | Description |
|---|---|---|
| text | Yes | Text to convert into speech. Supports 1–10000 characters. Inline audio tags can be included to guide delivery. |
| voice_id | Yes | Suggested voice name or custom voice ID. Default: Alice. |
| stability | No | Controls delivery consistency. Range: 0–1. Default: 0.5. |
| similarity | No | Controls similarity to the selected voice. Range: 0–1. Default: 0.75. |
[whispering] or [laughing] where needed.stability and similarity to tune the performance.Pricing is $0.08 per 1,000 input characters, prorated according to the actual length of text.
| Input Characters | Price |
|---|---|
| 100 | $0.008 |
| 500 | $0.040 |
| 1,000 | $0.080 |
| 10,000 | $0.800 |
Billable characters include the complete text field, including spaces, punctuation, and inline audio tags.
Requests shorter than 1,000 characters are billed proportionally rather than as a full 1,000-character block.
The calculated charge is rounded up to the nearest $0.000001.
voice_id, stability, and similarity do not add separate charges.
stability to adjust how consistent the performance remains across the script.similarity when you want to tune how closely the result follows the selected voice.text supports 1–10000 characters.Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/elevenlabs/eleven-v4 with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Eleven v4 below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"text": "[warmly] Welcome to a new day. Take a deep breath, find your rhythm, and make a little room for something wonderful.",
"voice_id": "Alice",
"stability": 0.5,
"similarity": 0.75
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/elevenlabs/eleven-v4" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d "$REQUEST_BODY")
TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
-H "Authorization: Bearer $WAVESPEED_API_KEY")
RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
case "$STATUS" in
completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout|deleted) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
*) sleep 2 ;;
esac
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/elevenlabs/eleven-v4";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
async function requestJson(url, options = {}) {
const response = await fetch(url, options);
if (!response.ok) throw new Error(await response.text());
return response.json();
}
// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
method: "POST",
headers: {
"Authorization": `Bearer ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"text": "[warmly] Welcome to a new day. Take a deep breath, find your rhythm, and make a little room for something wonderful.",
"voice_id": "Alice",
"stability": 0.5,
"similarity": 0.75
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;
// 2. Poll until the prediction finishes.
while (true) {
const resultBody = await requestJson(resultUrl, {
headers: { "Authorization": `Bearer ${apiKey}` },
});
const result = resultBody.data ?? resultBody;
if (result.status === "completed") {
console.log(result.outputs);
break;
}
if (["failed", "cancelled", "timeout", "deleted"].includes(result.status)) throw new Error(JSON.stringify(result));
await new Promise(resolve => setTimeout(resolve, 2000));
}import json
import os
import time
from urllib.request import Request, urlopen
api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
"text": "[warmly] Welcome to a new day. Take a deep breath, find your rhythm, and make a little room for something wonderful.",
"voice_id": "Alice",
"stability": 0.5,
"similarity": 0.75
}
def request_json(url, data=None):
request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
with urlopen(request) as response:
return json.load(response)
# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/elevenlabs/eleven-v4", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
raise RuntimeError("Submission response did not contain a prediction id")
result_url = f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"
# 2. Poll until the prediction finishes.
while True:
result_body = request_json(result_url)
result = result_body.get("data", result_body)
status = result.get("status")
if status == "completed":
print(result.get("outputs", []))
break
if status in {"failed", "cancelled", "timeout", "deleted"}:
raise RuntimeError(result)
time.sleep(2)Eleven v4 is a ElevenLabs model for audio generation, exposed as a REST API on WaveSpeedAI. Eleven V4 Text-to-Speech converts text into expressive multilingual speech with configurable voice selection, stability, and similarity controls for narration, dialogue, localization, virtual assistants, and voice production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates Python, JavaScript, and cURL examples for submitting requests and polling results. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/elevenlabs/elevenlabs-eleven-v4.
Eleven v4 starts at $0.08 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
Key inputs: `similarity`, `stability`, `text`, `voice_id`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/elevenlabs/elevenlabs-eleven-v4.
Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.
Commercial usage rights depend on the model's license, set by its provider (ElevenLabs). Check the provider's applicable terms and WaveSpeedAI's Terms of Service before commercial use.