Minimax Speech 02 Hd API Documentation

Minimax Speech 02 Hd API Documentation

Playground

Minimax Speech 02 HD is Minimax’s high-definition text-to-speech model delivering clear HD voices; pricing $0.05 per 1,000 characters. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

MiniMax Speech-02-HD is a high-definition text-to-speech (TTS) model that brings your words to life with natural pronunciation and studio-grade clarity. Perfect for creators, educators, and developers, it supports multi-lingual voices, flexible speed / volume / pitch controls, and delivers audio that sounds as if recorded by a real human voice actor. 🎧

🌟 Why it sounds great

• 🎵 High-definition synthesis: captures human-like tone, rhythm, and emotional nuance.
• 🌍 Multi-lingual support: speaks English, Chinese, Japanese, Korean, Spanish, and more — with accent-aware precision.
• 🗣️ Clear articulation: crisp and natural delivery, free from robotic noise or digital distortion.
• 🎚️ Adjustable parameters: control speed, volume, and pitch to match your desired energy and mood.
• 👥 Multiple voice options: choose from a diverse library of professional male, female, and regional voices.
• ⚡ Real-time streaming capabilities: generate and play audio as it’s being synthesized, enabling low-latency experiences for live applications.

⚙️ Limits and Performance

• 🧾 Max input length: up to 10,000 characters per request
• ⚡ Processing speed: around 1–2 seconds of real time per second of audio
• 🎧 Output format: MP3 or WAV
• 🌐 Languages: English, Chinese, Japanese, Korean, Spanish, and more

For the full multilingual voice list, see this document.

Pricing

Pricing is $0.10 per 1,000 input characters, calculated proportionally.

🚀 How to Use

1. ✍️ Enter or upload your text (≤10,000 characters).
2. 🧠 Choose your voice ID and language_boost.
3. 🎚️ Adjust speed, volume, and pitch if needed.
4. ▶️ Click Generate Audio — preview or download your file in MP3/WAV/PCM/FLAC, or use streaming mode for instant real-time playback.

💡 Pro Tips for Best Quality

• Use short sentences for smoother rhythm.
• For narration, try a slightly slower speed and lower pitch.
• Include punctuation — it helps the voice breathe naturally.
• Choose HD voices for podcasts, ads, or commercial projects.
• Use streaming mode for interactive or live-response scenarios.

📝 Notes

• The generation time will also depends on the selections you choose, like bitrate and channel.
• You can also find some guidance in this article: Build your digital human.

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_id": "your-voice-id",
  "speed": 1,
  "volume": 1,
  "pitch": 0,
  "emotion": "happy",
  "english_normalization": false,
  "sample_rate": 8000,
  "bitrate": 32000,
  "channel": "1",
  "format": "mp3",
  "language_boost": "Chinese"
}
JSON
)

# 1. Submit the prediction once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --connect-timeout 10 --max-time 60 \
  -X POST "https://api.wavespeed.ai/api/v3/minimax/speech-02-hd" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}"); then
  printf 'Submit failed. %s\n' "${CHECK}" >&2
  exit 1
fi

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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id. %s\n' "${CHECK}" >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
  # Transient errors (429, 5xx) are retried, honoring Retry-After.
  HTTP_CODE=$(curl --silent --show-error --fail-with-body \
    --connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
    --output "${BODY_FILE}" --write-out '%{http_code}' \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
  case "${HTTP_CODE}" in
    2??) ;;
    000|429|5??)  # dropped connection or temporary error: keep polling
      printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      sleep 10; continue ;;
    *) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      cat "${BODY_FILE}" >&2; exit 1 ;;
  esac
  RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted)
      printf 'Task %s ended with status %s\n' "${PREDICTION_ID}" "${STATUS}" >&2
      printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Every model also accepts the global request options enable_sync_mode and enable_base64_output; see their pages for details.

Response Parameters

Result Request Parameters

Result Response Parameters