Qwen3 Tts Voice Design

Qwen3 Tts Voice Design

Playground

Qwen3 TTS Voice Design: Generate speech with custom voice characteristics described in natural language. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Features

Qwen3-TTS Voice Design is a next-generation text-to-speech model that lets you design custom voices using natural language descriptions. Instead of selecting from preset voices, simply describe the voice you want — age, gender, tone, speaking style — and the model generates speech that matches your description.

Why Choose This?

• Natural language voice control Describe your ideal voice in plain text (e.g., “a warm, friendly female voice with a slight British accent”) and the model creates it.

• Unlimited voice variety No preset limits — create any voice character you can describe, from professional narrators to unique personas.

• Multilingual support Generate speech in 10 languages: Chinese, English, German, Italian, Portuguese, Spanish, Japanese, Korean, French, and Russian.

• Auto language detection Set language to “auto” and the model intelligently detects the language from your text.

Parameters

Voice Description Examples

• “A young female voice, energetic and cheerful, speaking quickly with enthusiasm”
• “An elderly male narrator with a deep, calm, authoritative tone”
• “A professional newsreader voice, neutral and clear, with perfect pronunciation”
• “A warm, friendly customer service representative, patient and helpful”
• “A dramatic storyteller voice with expressive intonation and theatrical pauses”

How to Use

1. Enter your text — write or paste the content you want to convert to speech.
2. Describe your voice — use natural language to describe the voice characteristics you want (age, gender, tone, style, accent, etc.).
3. Select language — choose the target language or use “auto” for automatic detection.
4. Run — submit and download your audio file.

Pricing

Billing Rules

• Minimum charge: $0.005 (for texts under 100 characters)
• For longer texts: $0.005 × (character count / 100)

Best Use Cases

• Character Voices — Create unique voices for games, animations, or audiobooks without voice actors.
• Prototyping — Quickly test different voice styles before committing to production.
• Localization — Generate consistent voice styles across multiple languages.
• Accessibility — Convert text to speech with customized, natural-sounding voices.
• Content Creation — Produce voiceovers for videos, podcasts, and presentations.

Pro Tips

• Be specific in your voice description — include age, gender, emotional tone, speaking pace, and any accent preferences.
• Use descriptive adjectives: “warm”, “crisp”, “authoritative”, “playful”, “soothing”, etc.
• Mention the context if relevant (e.g., “suitable for a children’s audiobook” or “professional corporate presentation”).
• Test with short text first to fine-tune your voice description before generating longer content.
• Combine multiple attributes for more nuanced voices (e.g., “middle-aged, confident but approachable”).

Notes

• Voice descriptions work best when they are clear and detailed.
• The same voice description will produce consistent results across multiple generations.
• For best quality, match the language parameter to your text content.

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'
{
  "text": "A clear example input",
  "voice_description": "A clear example input",
  "language": "auto"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/qwen3-tts/voice-design" \
  -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