MiniMax Speech 2.8 Turbo

Text-to-Speech • MiniMax • Proxied

MiniMax Speech 2.8 Turbo turns text into natural, expressive speech with voice cloning, emotion control, and 40+ language support at faster speeds.

Model Info
Terms and License	link ↗
More information	link ↗
Pricing	View pricing in the Cloudflare dashboard ↗

Usage

TypeScript
cURL

const response = await env.AI.run(
  'minimax/speech-2.8-turbo',
  {
    format: 'mp3',
    pitch: 0,
    speed: 1,
    text: 'Hello! Welcome to Cloudflare AI Gateway. Let me show you what we can do.',
    voice_id: 'English_expressive_narrator',
    volume: 1,
  },
)
console.log(response)

curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "minimax/speech-2.8-turbo",
  "input": {
    "format": "mp3",
    "pitch": 0,
    "speed": 1,
    "text": "Hello! Welcome to Cloudflare AI Gateway. Let me show you what we can do.",
    "voice_id": "English_expressive_narrator",
    "volume": 1
  }
}'

Output
Raw response

{
  "gatewayMetadata": {
    "keySource": "Unified"
  },
  "result": {
    "audio": "https://pub-04a6d208d361438ea01b797e6973bd19.r2.dev/catalog/minimax__speech-2.8-turbo/simple-speech.mp3"
  },
  "state": "Completed"
}

Examples

Fast Narration — Speed up narration for quick playback

TypeScript
cURL

const response = await env.AI.run(
  'minimax/speech-2.8-turbo',
  {
    format: 'mp3',
    pitch: 0,
    speed: 1.5,
    text: 'This is a fast-paced summary of the key findings from the quarterly report. Revenue is up fifteen percent and user growth exceeded expectations.',
    voice_id: 'English_expressive_narrator',
    volume: 1,
  },
)
console.log(response)

curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "minimax/speech-2.8-turbo",
  "input": {
    "format": "mp3",
    "pitch": 0,
    "speed": 1.5,
    "text": "This is a fast-paced summary of the key findings from the quarterly report. Revenue is up fifteen percent and user growth exceeded expectations.",
    "voice_id": "English_expressive_narrator",
    "volume": 1
  }
}'

Output
Raw response

{
  "gatewayMetadata": {
    "keySource": "Unified"
  },
  "result": {
    "audio": "https://pub-04a6d208d361438ea01b797e6973bd19.r2.dev/catalog/minimax__speech-2.8-turbo/fast-narration.mp3"
  },
  "state": "Completed"
}

Calm Tone — Calm and steady speech for meditation or relaxation

TypeScript
cURL

const response = await env.AI.run(
  'minimax/speech-2.8-turbo',
  {
    emotion: 'calm',
    format: 'mp3',
    pitch: 0,
    speed: 0.8,
    text: 'Take a deep breath in. Hold it for a moment. Now slowly exhale. Let your shoulders relax and release any tension.',
    voice_id: 'English_expressive_narrator',
    volume: 1,
  },
)
console.log(response)

curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "minimax/speech-2.8-turbo",
  "input": {
    "emotion": "calm",
    "format": "mp3",
    "pitch": 0,
    "speed": 0.8,
    "text": "Take a deep breath in. Hold it for a moment. Now slowly exhale. Let your shoulders relax and release any tension.",
    "voice_id": "English_expressive_narrator",
    "volume": 1
  }
}'

Output
Raw response

{
  "gatewayMetadata": {
    "keySource": "Unified"
  },
  "result": {
    "audio": "https://pub-04a6d208d361438ea01b797e6973bd19.r2.dev/catalog/minimax__speech-2.8-turbo/calm-tone.mp3"
  },
  "state": "Completed"
}

Adjusted Pitch — Lower the pitch for a deeper voice

TypeScript
cURL

const response = await env.AI.run(
  'minimax/speech-2.8-turbo',
  {
    format: 'mp3',
    pitch: -6,
    speed: 1,
    text: 'Good evening. Tonight we explore the mysteries of the deep ocean and the creatures that live in total darkness.',
    voice_id: 'English_expressive_narrator',
    volume: 1,
  },
)
console.log(response)

curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "minimax/speech-2.8-turbo",
  "input": {
    "format": "mp3",
    "pitch": -6,
    "speed": 1,
    "text": "Good evening. Tonight we explore the mysteries of the deep ocean and the creatures that live in total darkness.",
    "voice_id": "English_expressive_narrator",
    "volume": 1
  }
}'

Output
Raw response

{
  "gatewayMetadata": {
    "keySource": "Unified"
  },
  "result": {
    "audio": "https://pub-04a6d208d361438ea01b797e6973bd19.r2.dev/catalog/minimax__speech-2.8-turbo/adjusted-pitch.mp3"
  },
  "state": "Completed"
}

emotion

stringenum: happy, sad, angry, fearful, disgusted, surprised, calm, fluentEmotion control for synthesized speech

format

stringrequireddefault: mp3enum: mp3, flac, wavOutput audio format

pitch

integerrequireddefault: 0maximum: 12minimum: -12Pitch adjustment (-12 to 12)

▶sample_rate

one of

speed

numberrequireddefault: 1maximum: 2minimum: 0.5Speech speed (0.5 to 2)

text

stringrequiredmaxLength: 10000The text to convert to speech. Maximum 10,000 characters.

voice_id

stringrequireddefault: English_expressive_narratorThe voice ID to use for synthesis

volume

numberrequireddefault: 1maximum: 10minimum: 0Speech volume (0 to 10)

audio

stringURL to the generated audio file

API Schemas (Raw)

Input

Output