MiniMax Speech 2.8 HD API

Introduction

MiniMax Speech 2.8 HD reads a script aloud in one of 472 system voices, with a chosen emotion and performed sound tags, and returns one audio file per task: a 32 kHz mono MP3 unless you set the output format. The language is detected from the script, and language can hint one of 40 languages. There is no voice cloning and no upload of a reference voice.

Key features

A large voice library

voice_id takes one of 472 system voices, such as Calm_Woman, Deep_Voice_Man, Lively_Girl or Elegant_Man, and defaults to Calm_Woman.

One emotion for the whole read

emotion takes one of seven fixed values, neutral, happy, sad, angry, fearful, disgusted or surprised, and applies to the whole reading. It defaults to neutral.

Sounds inside the script

Tags in parentheses inside text, such as (sighs), (laughs), (breath) or (gasps), are performed as sounds rather than read aloud.

40 languages

Mandarin, Cantonese, English, Arabic, Russian, Spanish, French, Portuguese, German, Japanese, Italian, Korean, Polish and more. A language hint improves pronunciation on short or mixed scripts.

Output you can drop into any pipeline

output_format picks mp3 (default), wav, flac or pcm; sample_rate goes from 8000 to 44100 Hz, bitrate sets the MP3 bitrate and audio_channels switches to stereo.

Request parameters

Pricing

Prices are in credits, the same credits you use on the website (1 credit = $0.01). The hold is taken when the task is accepted and settled to the actual charge when it finishes; failed tasks are refunded.

For an exact number before you run, send the same body to POST /jobs/quote.

Use cases

Product and brand voiceovers

Pick a voice that fits the brand, keep emotion at neutral or happy, and use the pronunciation dictionary for product names.

Localised narration

One script per language with a language hint gives consistent narration across markets from the same voice library.

Characters and games

Emotions and sound tags give lines a performance: a fearful whisper, an angry shout, a laugh mid-sentence.

Prompt guide & pro tips

Fix names with the pronunciation dictionary

pronunciation_dict takes up to 100 {alias, pronunciation} pairs, so a name, acronym or loanword is always read the way you want: plain words or IPA in parentheses.

Let English numbers read naturally

english_normalization reads numbers, dates and abbreviations in English text the way a person would say them.

Choose wav over pcm for previews

pcm is raw 16-bit little-endian samples with no header, so it cannot be previewed in a browser; choose wav for the same samples in a playable file.

Split scripts that change mood

Because emotion applies to the whole task, send a scene that moves from calm to angry as separate tasks and join the files.

API quick start

Call the MiniMax Speech 2.8 HD API in three steps

1. Create an API key. Sign in to PopNow and create a key in the API console. Keys start with sk-popnow- and use the same credits as the website.
2. Send the request. POST /jobs/createTask with model minimax/speech-2.8-hd/text-to-speech and an input object that follows the parameter table. The response returns a task ID straight away.
3. Get the result. Poll GET /jobs/recordInfo with the task ID, or pass a callBackUrl and we post the result to it. Download the output links when the task succeeds.

# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(uuidgen)"
curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -d '{
  "model": "minimax/speech-2.8-hd/text-to-speech",
  "input": {
    "text": "Welcome back. Your files finished rendering a minute ago and are ready to download.",
    "voice_id": "Calm_Woman",
    "emotion": "neutral",
    "language": "auto",
    "output_format": "mp3"
  }
}'

# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

Replace the prompt and any links with your own. The API tab has the response, polling and callback reference.

MiniMax Speech 2.8 HD API questions

All MiniMax models

MiniMax Speech 2.8 Turbo uses the same voices at a lower price and returns faster. HD is the one for finished narration where audio quality matters.

• MiniMax H3 APIExpressive clips with audio, up to 2KFrom 28 credits for a 5-second clip
• MiniMax Speech 2.8 HD APIHigh-fidelity speech in 400+ voices with emotion controlFrom 18 credits per 1,000 characters
• MiniMax Music 3.0 APIFinished stereo songs, with vocals or instrumentalFrom 27 credits per run
• MiniMax H3 Singularity LoRA APICommunity-tuned H3 video that loads your own LoRAsFrom 45 credits for a 5-second clip
• MiniMax H3 Max APIFast clips with ambience, effects and musicFrom 38 credits for a 5-second clip
• MiniMax H3 LoRA APIMiniMax H3 video with sound and up to three of your LoRAsFrom 38 credits for a 5-second clip
• MiniMax H3 Image LoRA APIH3 stills and edits with up to three of your LoRAsFrom 7 credits per image
• MiniMax Speech 2.8 Turbo APIFast speech in 400+ voices with emotion controlFrom 11 credits per 1,000 characters

Other audio APIs

• Gemini 3.8 Flash TTS APIExpressive speech that acts out cues like [laughing]From 0.05 credits per second
• Gemini 3.8 Flash-Lite TTS APIFast, lightweight speech in 30 voicesFrom 0.03 credits per second
• Grok TTS API71 voices across 20 languages with speech tagsFrom 3 credits per 1,000 characters
• Seed Speech 2.0 API41 voices with tone set in plain languageFrom 11 credits per 1,000 characters
• Qwen3 TTS APIOpen-source speech with tone and pace set in plain wordsFrom 11 credits per 1,000 characters
• Chatterbox APIEnglish speech that can match a short voice sampleFrom 6 credits per run

More about MiniMax Speech 2.8 HD

Try it

MiniMax Speech 2.8 HD AI Voice Generator onlineCreate audio with MiniMax Speech 2.8 HD in PopNow

Docs

MiniMax Speech 2.8 HD model ID and input schema in the API docsPopNow API quickstart: your first request in five minutesWebhooks: get MiniMax Speech 2.8 HD results without polling