Model ID
Use with the Workers AI binding, the AI Gateway REST API, or the Unified API.
Calling the provider directly? Use the provider's model name instead, including with provider-native endpoints or the provider's own SDK. For example, Anthropic's name for anthropic/claude-opus-4.8 is claude-opus-4-8.
- Third-party
MiniMax Speech 02 HD is a studio-quality multilingual text-to-speech model with emotion control and support for cloned and designed voices.
| Model Info | |
|---|---|
| Terms and License | link ↗ |
| More information | link ↗ |
| Pricing |
|
const response = await env.AI.run(
'minimax/speech-02-hd',
{
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 $CLOUDFLARE_API_TOKEN" \
--header "Content-Type: application/json" \
--data '{
"model": "minimax/speech-02-hd",
"input": {
"format": "mp3",
"pitch": 0,
"speed": 1,
"text": "Hello! Welcome to Cloudflare AI Gateway. Let me show you what we can do.",
"voice_id": "English_expressive_narrator",
"volume": 1
}
}'{
"state": "Completed",
"result": {
"audio": "https://examples.aig.cloudflare.com/minimax/speech-02-hd/simple-speech.mp3"
}
}Custom Voice — Use a specific voice and adjust speed
const response = await env.AI.run(
'minimax/speech-02-hd',
{
format: 'mp3',
pitch: 0,
speed: 0.9,
text: 'The weather today is sunny with a high of 72 degrees. Perfect for a walk in the park.',
voice_id: 'English_expressive_narrator',
volume: 1,
},
)
console.log(response)curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
--header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
--header "Content-Type: application/json" \
--data '{
"model": "minimax/speech-02-hd",
"input": {
"format": "mp3",
"pitch": 0,
"speed": 0.9,
"text": "The weather today is sunny with a high of 72 degrees. Perfect for a walk in the park.",
"voice_id": "English_expressive_narrator",
"volume": 1
}
}'{
"state": "Completed",
"result": {
"audio": "https://examples.aig.cloudflare.com/minimax/speech-02-hd/custom-voice.mp3"
}
}With Emotion — Apply emotional tone to speech
const response = await env.AI.run(
'minimax/speech-02-hd',
{
emotion: 'happy',
format: 'mp3',
pitch: 0,
speed: 1,
text: "Congratulations! You've just won the grand prize! This is absolutely incredible news!",
voice_id: 'English_expressive_narrator',
volume: 1,
},
)
console.log(response)curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
--header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
--header "Content-Type: application/json" \
--data '{
"model": "minimax/speech-02-hd",
"input": {
"emotion": "happy",
"format": "mp3",
"pitch": 0,
"speed": 1,
"text": "Congratulations! You'\''ve just won the grand prize! This is absolutely incredible news!",
"voice_id": "English_expressive_narrator",
"volume": 1
}
}'{
"state": "Completed",
"result": {
"audio": "https://examples.aig.cloudflare.com/minimax/speech-02-hd/with-emotion.mp3"
}
}High Sample Rate — Studio quality at 44.1kHz sample rate
const response = await env.AI.run(
'minimax/speech-02-hd',
{
format: 'mp3',
pitch: 0,
sample_rate: 44100,
speed: 1,
text: 'This recording is generated at studio quality sample rate for the highest possible audio fidelity.',
voice_id: 'English_expressive_narrator',
volume: 1,
},
)
console.log(response)curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
--header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
--header "Content-Type: application/json" \
--data '{
"model": "minimax/speech-02-hd",
"input": {
"format": "mp3",
"pitch": 0,
"sample_rate": 44100,
"speed": 1,
"text": "This recording is generated at studio quality sample rate for the highest possible audio fidelity.",
"voice_id": "English_expressive_narrator",
"volume": 1
}
}'{
"state": "Completed",
"result": {
"audio": "https://examples.aig.cloudflare.com/minimax/speech-02-hd/high-sample-rate.mp3"
}
}text
stringrequiredmaxLength: 10000The text to convert to speech. Maximum 10,000 characters.voice_id
stringrequireddefault: English_expressive_narratorThe voice ID to use for synthesisspeed
numberrequireddefault: 1minimum: 0.5maximum: 2Speech speed (0.5 to 2)volume
numberrequireddefault: 1minimum: 0maximum: 10Speech volume (0 to 10)pitch
integerrequireddefault: 0minimum: -12maximum: 12Pitch adjustment (-12 to 12)emotion
stringenum: happy, sad, angry, fearful, disgusted, surprised, calmEmotion control for synthesized speechformat
stringrequireddefault: mp3enum: mp3, flac, wavOutput audio format▶sample_rate
one ofaudio
stringURL to the generated audio file