Minimax Speech 2.8 Turbo API Documentation

Minimax Speech 2.8 Turbo API Documentation

Playground

MiniMax Speech 2.8 Turbo is a high-definition text-to-speech model with natural and expressive voice synthesis. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

MiniMax Speech 2.8 Turbo is a high-quality text-to-speech model that transforms written text into natural, expressive audio. With support for multiple voice presets, emotional tones, and fine-grained audio controls, it delivers broadcast-ready speech synthesis for any application.

Why Choose This?

• Rich voice library Choose from 17+ preset voices spanning different genders, ages, and speaking styles — or use your own custom-trained voice.

• Expressive interjections Add natural human sounds like (laughs), (sighs), (coughs), (gasps), and more directly in your text for lifelike delivery.

• Emotion control Set the emotional tone of the speech — happy, calm, or other moods — to match your content.

• Pronunciation customization Define custom pronunciations for brand names, acronyms, or specialized terms using the pronunciation dictionary.

• Full audio control Fine-tune speed, volume, pitch, sample rate, bitrate, channel, and output format for production-ready results.

Parameters

Available Voices

Wise_Woman, Friendly_Person, Inspirational_girl, Deep_Voice_Man, Calm_Woman, Casual_Guy, Lively_Girl, Patient_Man, Young_Knight, Determined_Man, Lovely_Girl, Decent_Boy, Imposing_Manner, Elegant_Man, Abbess, Sweet_Girl_2, Exuberant_Girl

You can also use a custom voice ID trained via MiniMax Voice Clone.

Supported Interjections

(laughs), (chuckle), (coughs), (clear-throat), (groans), (breath), (pant), (inhale), (exhale), (gasps), (sniffs), (sighs), (snorts), (burps), (lip-smacking), (humming), (hissing), (emm), (whistles), (sneezes), (crying), (applause)

How to Use

1. Enter your text — write or paste the content you want to convert to speech.
2. Select voice_id — choose a preset voice or enter your custom voice ID.
3. Adjust speech settings (optional) — modify speed, volume, and pitch as needed.
4. Set emotion (optional) — select the emotional tone for the delivery.
5. Configure audio output (optional) — choose sample rate, bitrate, channel, and format.
6. Run — submit and download your audio file.

Pricing

Best Use Cases

• Audiobook Production — Convert manuscripts into natural-sounding narration with expressive voices.
• Video Voiceovers — Generate professional voiceovers for YouTube, ads, or explainer videos.
• Podcasts & Broadcasting — Create consistent voice content without recording equipment.
• E-learning & Training — Produce clear, engaging audio for educational materials.
• Accessibility — Convert written content to audio for visually impaired users.
• Game & App Development — Add character voices and UI narration to interactive experiences.

Pro Tips

• Use interjections sparingly for natural effect — too many can sound unnatural.
• Match voice_id to your content: use “Deep_Voice_Man” or “Imposing_Manner” for authoritative content, “Lively_Girl” or “Casual_Guy” for friendly content.
• Enable english_normalization when your text contains numbers, dates, or currencies.
• Use pronunciation_dict for consistent handling of brand names or technical terms.
• Start with default speed/pitch settings, then adjust based on your specific use case.

Notes

• Text length affects processing time and cost — longer texts take more time.
• For custom voices, train your voice model first via Voice Clone.
• Interjections must be written in parentheses exactly as listed to be recognized.

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-2.8-turbo" \
  -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