MiniMax Voice Design generates natural voices from textual descriptions - no cloning - lets you set tone, accent and personality. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Bereit
$0.5pro Durchlauf·~20 / $10
Excited and enthusiastic male product reviewer (e.g., tech vlogger), fast-paced, high energy, and persuasive.
Warm, soft-spoken female voice with a gentle tone, medium-slow pace, soothing
Deep, gravelly male voice, calm and serious, slow and measured pace
Energetic, bright female voice, slightly high-pitched, excited emotion, fast-paced
oung male voice, curious and expressive, mid-speed with rising intonation
Elderly female voice, soft and nostalgic, slow-paced, gentle vibrato
Confident, assertive female voice, professional tone, medium-fast pace
Teenage male voice, casual and laid-back, slight sarcasm, mid-speed
Robotic neutral voice, genderless, steady rhythm, monotone but clear articulation
Deep, dramatic male voice, cinematic trailer style, slow and intense
Sweet, childlike female voice, playful and whimsical, fast tempo
MiniMax Voice Design is a state-of-the-art voice synthesis model developed by MiniMax. Instead of cloning a voice from a reference audio, it generates high-quality voices based on your textual voice description, allowing you to create speech with the desired tone, accent, and personality.
High-Fidelity Voice Generation Produces speech that matches your description with natural prosody and pronunciation.
Flexible Voice Design Create a wide range of voices by simply describing the desired characteristics—no reference audio required.
Emotion and Tone Control Fine-tune speaking style and emotion for storytelling, games, and character dialogue.
Multilingual Output Supports voice design across different languages and smooth code-switching.
Low-Latency Inference Optimized for real-time use cases, including live interactions and dialogue generation.
MiniMax Voice Design uses a neural TTS pipeline with robust speaker and prosody modeling. By leveraging your textual description, it offers clarity, control, and speed, delivering production-ready results in diverse environments.
Your custom voice ID must be used at least once with one of the voice models on our platform to be saved permanently. Such as:
Otherwise, we can only store it for 7 days. After that, it will be deleted and the voice ID will no longer be callable.
For easier reuse later, please make sure to use your voice ID once in one of the models above after creating it.
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/minimax/voice-design 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 Voice Design below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"custom_voice_id": "example",
"text": "A clear example input"
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/minimax/voice-design" \
-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/minimax/voice-design";
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 ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"custom_voice_id": "example",
"text": "A clear example input"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${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 = {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"custom_voice_id": "example",
"text": "A clear example input"
}
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/minimax/voice-design", 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)Voice Design is a MiniMax model for audio generation, exposed as a REST API on WaveSpeedAI. MiniMax Voice Design generates natural voices from textual descriptions - no cloning - lets you set tone, accent and personality. 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/minimax/minimax-voice-design.
Voice Design starts at $0.50 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: `prompt`, `custom_voice_id`, `text`. 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/minimax/minimax-voice-design.
Average end-to-end generation time on WaveSpeedAI is around 30 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Commercial usage rights depend on the model's license, set by its provider (MiniMax). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.