Transform text into natural, expressive speech with MiniMax TTS. Powered by Speech-02 technology with emotion control, speed adjustment, and real-time synthesis.
No credit card required • Real-time synthesis • Commercial license included
Choose the right model for your application
Best Quality
Best for: Audiobooks, Podcasts, Premium Content
Best Speed
Best for: Live Apps, Chatbots, Gaming
Best Value
Best for: Testing, Prototypes, Large-scale
Everything you need for professional voice synthesis
Comprehensive language support including English, Spanish, French, German, Japanese, Korean, Arabic, Hindi, Portuguese, Russian, and many more.
Generate speech with 7 different emotions: neutral, happy, sad, angry, fearful, surprised, and disgusted. Perfect for dynamic storytelling.
Adjust speech speed from 0.5x to 2.0x with 0.1 increments. Maintain natural prosody and intonation at any speed.
Access 300+ built-in voices with diverse accents, genders, and ages. Male, female, child voices with regional accents.
Fine-tune voice pitch to match your needs. Adjust from -12 to +12 semitones while maintaining natural voice quality.
Generate speech in real-time with ultra-low latency. Perfect for live applications, chatbots, and interactive experiences.
Transform how you create audio content
Generate voiceovers for videos, podcasts, and audiobooks with studio-quality voices. Scale production without recording equipment.
Create engaging educational content with natural-sounding voices in any language. Perfect for course creators and trainers.
Power IVR systems, voice assistants, and customer support with natural conversational voices that improve user experience.
Generate character dialogue, NPC voices, and dynamic narration for games, apps, and interactive media.
POST https://api.minimax.io/v1/t2a_v2
curl -X POST \
https://api.minimax.io/v1/t2a_v2 \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "speech-2.6-hd",
"text": "Hello world",
"voice_id": "male-qn-qingse",
"speed": 1.0,
"vol": 1.0,
"pitch": 0,
"emotion": "neutral",
"audio_sample_rate": 32000,
"bitrate": 128000,
"format": "mp3"
}'
{
"audio_file": "base64_audio_data",
"trace_id": "abc123xyz",
"base_resp": {
"status_code": 0,
"status_msg": "success"
},
"extra_info": {
"audio_length": 2.5,
"audio_size": 40960,
"audio_sample_rate": 32000,
"bitrate": 128000
}
}
+ 24 more languages supported
Generate studio-quality speech in 40+ languages with full emotion control
Free tier available • No credit card required • Commercial license included