Inworld Realtime TTS-2 converts text into low-latency, natural speech with official TTS-2 controls for delivery mode, language, timestamps, text normalization, and audio output settings. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
निष्क्रिय
$0.035प्रति रन·~28 / $1
Inworld Realtime TTS 2 converts text into natural-sounding speech with low-latency generation and flexible voice controls. It supports multiple output audio formats and lets you adjust speaking rate and temperature for different delivery styles.
Low-latency text-to-speech Generate speech quickly for interactive apps, assistants, and real-time voice experiences.
Natural voice output Create smooth, human-like speech from plain text with selectable voices.
Flexible voice controls Adjust speaking rate and temperature to better match tone, pacing, and delivery style.
Multiple output formats
Export audio in MP3, LINEAR16, OGG_OPUS, FLAC, or WAV depending on your workflow.
Production-ready API Access the model through a realtime-friendly API for apps, agents, games, and voice products.
| Parameter | Required | Description |
|---|---|---|
| text | Yes | Input text to convert into speech. |
| voice_id | No | Voice selection for the generated speech, such as Julia. |
| speaking_rate | No | Controls how fast the voice speaks. Default: 1. |
| temperature | No | Controls variation and expressiveness in the generated speech. Default: 1. |
| output_format | No | Output audio format: MP3, LINEAR16, OGG_OPUS, FLAC, or WAV. |
MP3, LINEAR16, OGG_OPUS, FLAC, or WAV.Welcome to our product demo. Today we will walk through the key features, explain how the workflow operates, and show how quickly you can integrate voice output into your application.
| Text Length | Cost |
|---|---|
| 1–1000 chars | $0.035 |
| 1001–2000 chars | $0.070 |
| 2001–3000 chars | $0.105 |
| 3001–4000 chars | $0.140 |
| 4001–5000 chars | $0.175 |
text.1,000-character block.1,000 characters adds $0.035.voice_id, speaking_rate, temperature, and output_format do not affect pricing.speaking_rate to match the use case, such as slower for tutorials and faster for assistants.temperature when you want more variation in delivery style.MP3 for broad compatibility, and use lossless formats like WAV or FLAC when audio quality matters more.text is the only required field.MP3, LINEAR16, OGG_OPUS, FLAC, and WAV.Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/inworld/realtime-tts-2 with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Realtime Tts 2 below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"text": "A clear example input",
"voice_id": "Dennis",
"speaking_rate": 1,
"temperature": 1,
"output_format": "MP3"
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/inworld/realtime-tts-2" \
-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=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi
# 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' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
created|processing) sleep 2 ;;
*) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
esac
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/inworld/realtime-tts-2";
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 ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"text": "A clear example input",
"voice_id": "Dennis",
"speaking_rate": 1,
"temperature": 1,
"output_format": "MP3"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${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"].includes(result.status)) throw new Error(JSON.stringify(result));
if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
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": "A clear example input",
"voice_id": "Dennis",
"speaking_rate": 1,
"temperature": 1,
"output_format": "MP3"
}
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/inworld/realtime-tts-2", 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 = task.get("urls", {}).get("get") or 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"}:
raise RuntimeError(result)
if status not in {"created", "processing"}:
raise RuntimeError(f"Unexpected status: {status}")
time.sleep(2)Realtime Tts 2 is a Inworld model for audio generation, exposed as a REST API on WaveSpeedAI. Inworld Realtime TTS-2 converts text into low-latency, natural speech with official TTS-2 controls for delivery mode, language, timestamps, text normalization, and audio output settings. 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 production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/inworld/inworld-realtime-tts-2.
Realtime Tts 2 starts at $0.035 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: `enable_sync_mode`, `output_format`, `speaking_rate`, `temperature`, `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/inworld/inworld-realtime-tts-2.
Median end-to-end generation time on WaveSpeedAI is around 2 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.
Commercial usage rights depend on the model's license, set by its provider (Inworld). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.