Skip to main content
MindStudio
Pricing
BlogAbout
Log inGet Started
My Workspace
Text to Speech Model

Seed Speech TTS 2.0

Text to Speech by ByteDance

Start Building with Seed Speech TTS 2.0View All Models
PublisherByteDance
TypeText to Speech
Context Window10,000 tokens
Released2026
Price$60 / 1M characters
ProviderWaveSpeed
MULTILINGUAL
Try Seed Speech TTS 2.0 →

Ready to build with Seed Speech TTS 2.0?

Get Started Free
Resources

Documentation & links

Official Website
→
Configuration

Parameters & options

VoiceSelect

Preset voice, named with the languages it speaks.

Default: stokie_en
Vivi (English, Chinese, Japanese, Spanish, Indonesian)Mindy (English, Spanish, Indonesian, Portuguese, Chinese)Stokie (English)Dacey (English)Tim (English)Kian (English, Chinese)Cedric (English, Chinese)Sophie (English, Chinese)Jean (English, Chinese)Magnus (English, Chinese)Mabel (English, Chinese)Nadia (English, Chinese)Opal (English, Chinese)Pearl (English, Chinese)Quentin (English, Chinese)Vienna (English, Chinese)Alina (English, Chinese)Corinne (English, Chinese)Esther (English, Chinese)Freya (English, Chinese)Gigi (English, Chinese)Holly (English, Chinese)Lyla (English, Chinese)Daisy (English, Chinese)Tracy (Spanish, Chinese)Jess (Japanese, Spanish, Indonesian, Portuguese, English, Chinese)Pinky (Spanish, Korean, English, Chinese)Sweety (Japanese, Spanish)Sandy (Spanish, English, Chinese)Sven (German)Minimi (Japanese)Usseau (French)Felipe (Spanish)Han (Indonesian)Martins (Portuguese)Enzo (Italian)Shane (Korean)Bonnie (Chinese)Felix (Chinese)Celeste (Chinese)Monkey King (Chinese)
Voice InstructionPrompt

Optional direction for tone, emotion, pace or volume (e.g. "warm and unhurried"). It is never spoken.

LanguageSelect

Unset, the language is detected from the text.

ChineseEnglishJapaneseSpanish (Mexico)IndonesianPortuguese (Brazil)KoreanItalianGermanFrench
SpeedNumber

Speaking speed. 1.0 is normal.

Default: 1Range: 0.5–2 (step 0.05)
PitchNumber

Pitch shift in semitones. 0 is normal.

Default: 0Range: -12–12 (step 1)
VolumeNumber

Loudness. 1.0 is normal.

Default: 1Range: 0.5–2 (step 0.05)
Output FormatSelect
Default: mp3
MP3Opus
Sample RateSelect
Default: 24000
16,000 Hz24,000 Hz (default)44,100 Hz48,000 Hz
Related models

Explore similar models

ByteDance

Seedream 5.0 Flash

$0.027/image
10K
ByteDance

Seedance 2.5 Turbo

Seedance 2.5 Turbo is a video generation model from ByteDance that supports text-to-video, image-to-video, and video editing modes.

$1.00-$12.00/video
50K
ByteDance

Seedance 2.5

Seedance 2.5 is a video generation model from ByteDance that supports text-to-video, image-to-video, video editing, and audio generation.

$0.11-$1.10/second
50K
Google

Gemini 3.8 Flash-Lite TTS

$0.50/MTok
$6.00/MTok
6K
Qwen

Qwen Audio 3.0 TTS Plus

$20 / 1M characters
10K
Inworld

Inworld TTS-2

$35 / 1M characters
2K

Start building with Seed Speech TTS 2.0

No API keys required. Create AI-powered workflows with Seed Speech TTS 2.0 in minutes — free.

Get Started FreeExplore All Models