Seedream 5.0 Pro est en ligne | Essayez dans le Générateur d'images →

Microsoft Vibevoice | Realistic Voice & TTS

microsoft/

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.

text-to-audio
Entrée

En attente

$0.12par exécution·~83 / $10

ExemplesTout voir

Modèles associés

README

Microsoft VibeVoice

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.

Why Choose This?

  • 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.

Parameters

ParameterRequiredDescription
promptYesConversation script with speaker labels
speaker_1NoVoice for Speaker 0 (default: en-Alice_woman)
speaker_2NoVoice for Speaker 1
speaker_3NoVoice for Speaker 2
speaker_4NoVoice for Speaker 3
scaleNoVoice expressiveness (default: 1.3)

Available Voices

VoiceLanguageGender
en-Alice_womanEnglishFemale
en-Carter_manEnglishMale
en-Frank_manEnglishMale
en-Mary_woman_bgmEnglishFemale
en-Maya_womanEnglishFemale
in-Samuel_manIndianMale
zh-Anchen_man_bgmChineseMale
zh-Bowen_manChineseMale
zh-Xinran_womanChineseFemale

Prompt Format

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.

How to Use

  1. Write your script — create dialogue with Speaker 1, 2, 3, 4 labels.
  2. Assign voices — select a voice for each speaker.
  3. Adjust scale (optional) — increase for more expressive delivery, decrease for calmer tone.
  4. Run — submit and download your generated conversation.

Pricing

OutputCost
Per generation$0.12

Best Use Cases

  • Podcast Production — Generate multi-speaker podcast episodes.
  • Dialogue Prototyping — Preview conversational scripts before recording.
  • Audiobook Narration — Create multi-character dialogue scenes.
  • Language Learning — Produce natural conversation samples in multiple languages.
  • Video Voiceover — Generate dialogue tracks for video content.

Pro Tips

  • Use Speaker 1, 2, 3, 4 to label up to 4 different characters.
  • Mix male and female voices for more natural conversations.
  • Voices with "_bgm" suffix include background music.
  • Increase scale above 1.3 for more dramatic delivery, lower for neutral tone.
  • Combine English and Chinese speakers for bilingual conversations.

Notes

  • Only prompt is required; speaker voices default if not specified.
  • Speaker labels must use numbers 0-3 matching speaker_1 through speaker_4.
  • Maximum 4 speakers per generation.
  • Use the Prompt Enhancer to improve script quality.
Remarque :Ce site utilise des modèles d'IA fournis par des tiers.

Vibevoice API — Quick start

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.

HTTP example
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
done
Node.js example
const 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));
}
Python example
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 API — Frequently asked questions

What is the Vibevoice API?

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.

How do I call the Vibevoice API?

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.

How much does Vibevoice cost per run?

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.

What inputs does Vibevoice accept?

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.

How long does Vibevoice take to generate?

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.

Can I use Vibevoice outputs commercially?

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.

Microsoft Vibevoice | Realistic Voice & TTS API on WaveSpeedAI