WaveSpeed.ai
DashboardExploreInspiration
Home/Explore/Hailuo Video Models/minimax/speech-2.6-turbo

text-to-audio

minimax/speech-2.6-turbo

MiniMax Speech 2.6: Ultra-Fast, Ultra-Human, Ultra-Smart — redefining voice technology with < 250ms latency, natural voice cloning, seamless multilingual support across 40+ languages, and industry-leading text normalization for flawless, expressive communication anywhere, anytime. Your request will cost $0.06 per 1000 characters.

Hint: Desired voice ID. Use a voice ID you have trained (https://wavespeed.ai/models/minimax/voice-clone), or one of the following system voice IDs: 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
This parameter supports English text normalization, which improves performance in number-reading scenarios.
If enabled, the output will be encoded into a BASE64 string instead of a URL. This property is only available through the API.
If set to true, the function will wait for the result to be generated and uploaded before returning the response. It allows you to get the result directly in the response. This property is only available through the API.

Idle

Your request will cost $0.06 per run.

For $1 you can run this model approximately 16 times.

ExamplesView all

README

MiniMax Speech 2.6 Turbo

High-definition Text-to-Speech (TTS) with natural pronunciation and crisp articulation. Supports multiple built-in voices and custom cloned voices, adjustable speed, volume, and pitch, and coverage of 40+ languages for professional audio creation.

Features

  • Multilingual leap: Substantially improved English and overall multilingual similarity, accuracy, and rhythm vs. Speech 02; seamless switching across 40 languages for meetings, podcasts, and daily dialog.
  • Lifelike tone replication: Cross-language, accent, style, and emotion control with industry-leading nuance—including cross-language accent retention, regional accent preservation, and special age voice replication.
  • Global language set (40+): Expanded library including (new adds) Bulgarian, Danish, Hebrew, Malay, Persian, Slovak, Swedish, Croatian, Filipino, Hungarian, Norwegian, Slovenian, Catalan, Nynorsk, Tamil, Afrikaans, and more—great for cross-border commerce, customer support, and localized marketing.

How to Use

1) Choose a Voice (voice_id)

Use either a custom voice you trained (voice cloning) or a built-in system voice (case-sensitive):

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

2) Set Audio Parameters (mapped to the UI dropdowns)

  • english_normalization (boolean) Improves English text normalization, especially for number reading (e.g., “$1,299” → “one thousand two hundred ninety-nine dollars”).
  • sample_rate (Hz) Common: 22050, 24000, 44100, 48000. Tips: 44.1 kHz for music/podcasts; 48 kHz for video post-production.
  • bitrate (bps for MP3/OGG) 64k / 96k / 128k / 192k / 256k / 320k. Tips: ≥192k for distribution; 96–128k for previews.
  • channel: mono or stereo Mono is smaller/clearer for speech; stereo when spatialization is desired.
  • format: mp3, wav, ogg, flac, wav is lossless (bigger files); mp3 is compact and web-friendly.
  • language_boost (IETF code like en, zh, ja …) Prioritize the main language in mixed-language inputs.

Prosody controls

  • speed: speaking rate (e.g., 0.8–1.2).
  • volume: gain (unit depends on API; typically linear or dB).
  • pitch: pitch shift (semitones/cents or normalized value).

Price

Price: $0.06 / 1,000 characters

Typical Use Cases

  • Short-video and ad voiceovers, e-learning and courseware, AI assistants and IVR, podcasts/audiobooks, cross-border e-commerce localization.

Best-Practice Presets (optional)

  • Video voiceover: format=wav, sample_rate=48000, channel=mono, english_normalization=true.
  • Web preview: format=mp3, sample_rate=44100, bitrate=128000, channel=mono.
  • Podcast: format=mp3, sample_rate=44100, bitrate=192000–320000, channel=stereo if mixing music.