MiMo-V2.5-tts

Name: MiMo-V2.5-tts
Author: DeepInfra

tts

Automatically convert input text into natural and fluent speech output. You can generate natural and vivid speech content by configuring parameters such as speech style and voice. Use the high-quality voices from the built-in voices list.

Capabilities

Show unsupported (12)

Infrastructure

Streaming

Details

Model IDXiaomiMiMo/MiMo-V2.5-tts

ProviderDeepInfra

Creatorxiaomimimo

Familymimo

License—

Statusactive

Typetts

Input modalitiestext

Output modalitiesspeech

Open weightNo

Parameters—

Architecture—

Max chars—

Sample rate—

Voices—

Languages—

Release date—

Sourceofficial

Endpoints

audio speechPOST

https://api.deepinfra.com/v1/openai/audio-speech

Pricing

$0.0000 per 1M input characters

Family Comparison: mimo

Model	Caps	Max chars	Sample rate	Voices	Languages	Pricing
MiMo-V2.5-tts-voiceclone	S	—	—	—	—	—
MiMo-V2.5-tts-voicedesign	S	—	—	—	—	—
MiMo-V2.5-tts	S	—	—	—	—	—
MiMo-V2.5	RTJJMS	—	—	—	—	$0.14$0.28
MiMo-V2.6-Flash	RTJJMS	—	—	—	—	$0.14$0.28
MiMo-V2.6-Pro	RTJJMS	—	—	—	—	$0.43$0.87
MiMo-V2.5-Pro	RTJJMS	—	—	—	—	$1$3

API

GET/v1/models/deepinfra/XiaomiMiMo/MiMo-V2.5-tts