Alibaba Qwen3 Tts Flash

Alibaba Qwen3 Tts Flash

Playground

Qwen3 TTS Flash: Low-latency Text-to-Speech for English and Chinese with multiple voices, ideal for real-time dialogue. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Qwen3 TTS Flash is low-latency, natural-sounding Text-to-Speech model that supports English and Chinese with multiple voice styles. It is designed for real-time conversations, product narration, and short-form video dubbing.

Highlights

• Low latency / high concurrency for real-time interaction
• Multi-language / multi-style voices (English/Chinese priority)
• Parameter control: speed, pitch, volume, speaker (voice_id), emotion
• Production-ready: stable output, easy integration, common audio formats

Input & Parameters

• text (string, required): The text to synthesize (recommended < 2000 characters per request)
• voice_id (string, optional): Voice style ID (e.g., qwen-female-1, qwen-male-1; see platform docs for the full list)
• language (string, optional): Language code (en, zh)
• speed (number, optional): Speaking rate, default 1.0 (range 0.5–2.0)
• pitch (number, optional): Pitch adjustment, default 0
• volume (number, optional): Output gain, default 0
• emotion (string, optional): Voice emotion/style, e.g., neutral, happy, sad
• sample_rate (int, optional): Sample rate, default 22050 (e.g., 16000/22050/24000/44100)
• format (string, optional): Output format, default mp3 (supports mp3, wav, ogg)

Note: The available speakers and parameter ranges depend on the platform configuration.

Pricing

• Formula: total_price = base_price * text_length / 1000
• Current base_price: 1000 (unit depends on platform configuration)

Example

{ “model”: “/qwen3-tts-flash”, “input”: { “text”: “Hello, welcome to WaveSpeedAI!”, “voice_id”: “qwen-female-1”, “language”: “en”, “speed”: 1.0, “format”: “mp3” } }

Use Cases

• Real-time conversational agents / voice replies
• Short-form video, advertising, and e-commerce dubbing
• App/IoT voice prompts and announcements
• Education, customer service, and knowledge base narration

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": "Cherry",
  "language_type": "Auto"
}
JSON
)

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