Microsoft VibeVoice text-to-speech model generates long-form speech from text with multi-speaker dialogue support. Choose from 9 voice presets across English, Chinese, and Hindi. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Bereit
$0.12pro Durchlauf·~83 / $10
Microsoft VibeVoice is an advanced multi-speaker text-to-speech model that generates natural conversations between up to 4 speakers. Assign different voices to speakers in your script and the model produces realistic dialogue with natural turn-taking and expression.
Multi-speaker conversations Support up to 4 distinct speakers in a single generation.
Natural dialogue Realistic turn-taking and conversational flow between speakers.
Multilingual voices 9 preset voices across English, Chinese, and Indian languages.
Expression control Adjust voice expressiveness with the scale parameter.
Prompt Enhancer Built-in tool to automatically improve your scripts.
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Conversation script with speaker labels |
| speaker_1 | No | Voice for Speaker 0 (default: en-Alice_woman) |
| speaker_2 | No | Voice for Speaker 1 |
| speaker_3 | No | Voice for Speaker 2 |
| speaker_4 | No | Voice for Speaker 3 |
| scale | No | Voice expressiveness (default: 1.3) |
| Voice | Language | Gender |
|---|---|---|
| en-Alice_woman | English | Female |
| en-Carter_man | English | Male |
| en-Frank_man | English | Male |
| en-Mary_woman_bgm | English | Female |
| en-Maya_woman | English | Female |
| in-Samuel_man | Indian | Male |
| zh-Anchen_man_bgm | Chinese | Male |
| zh-Bowen_man | Chinese | Male |
| zh-Xinran_woman | Chinese | Female |
Write conversations using speaker labels. Each line starts with "Speaker N:" followed by the dialogue:
Speaker 1: Hey, have you tried the new VibeVoice model on WaveSpeedAI yet? Speaker 2: Not yet! What's so special about it? Speaker 1: It can generate really natural multi-speaker conversations like this one.
| Output | Cost |
|---|---|
| Per generation | $0.12 |
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/microsoft/vibevoice with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Vibevoice below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"speaker_1": "en-Alice_woman",
"speaker_2": "en-Alice_woman",
"speaker_3": "en-Alice_woman",
"speaker_4": "en-Alice_woman",
"scale": 1.3
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/microsoft/vibevoice" \
-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/microsoft/vibevoice";
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 ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"speaker_1": "en-Alice_woman",
"speaker_2": "en-Alice_woman",
"speaker_3": "en-Alice_woman",
"speaker_4": "en-Alice_woman",
"scale": 1.3
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${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",
"speaker_1": "en-Alice_woman",
"speaker_2": "en-Alice_woman",
"speaker_3": "en-Alice_woman",
"speaker_4": "en-Alice_woman",
"scale": 1.3
}
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/microsoft/vibevoice", 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)Vibevoice is a Microsoft model for audio generation, exposed as a REST API on WaveSpeedAI. Microsoft VibeVoice text-to-speech model generates long-form speech from text with multi-speaker dialogue support. Choose from 9 voice presets across English, Chinese, and Hindi. 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/microsoft/microsoft-vibevoice.
Vibevoice starts at $0.12 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`, `scale`, `speaker_1`, `speaker_2`, `speaker_3`, `speaker_4`. 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/microsoft/microsoft-vibevoice.
Median end-to-end generation time on WaveSpeedAI is around 115 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 (Microsoft). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.