Microsoft Vibevoice

Microsoft Vibevoice

Playground

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.

Features

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

Available Voices

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

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.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "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 "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(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' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  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

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters