M

MOSS-TTS

MOSS-TTSvfamilyCurrent
Released February 7, 2026
Context1 tokens
Price (In / Out)Free / Free
CategorySpeech Generation Model
Max Output1 tokens

About MOSS-TTS

MOSS-TTS Family is an open-source speech and sound generation model family from MOSI.AI and the OpenMOSS team. It covers long-form speech, multi-speaker dialogue, voice and character design, environmental sound effects, and streaming TTS.

Capabilities

text to speechaudio generationvoice designstreaming tts

Input Modalities

textaudio

Output Modalities

audio

Technical Details

API Identifier
https://github.com/OpenMOSS/MOSS-TTS
Category
Speech Generation Model
Context Window
1 tokens
Max Output Tokens
1 tokens

Tags

open-sourcegithubai-modelresearchmoss-tts

Pricing

Token pricing for MOSS-TTS API usage.

Input Tokens

Free

per million tokens

Output Tokens

Free

per million tokens

Pricing Calculator

Input cost$0.00
Output cost$0.00
Estimated monthly cost$0.00

Open-source repository; API pricing is not listed as a hosted commercial API in the reviewed source. Operating cost depends on self-hosting, compute, and deployment choices. Context and output token fields are marked as 1 because the schema requires numeric values for non-text model families where token context is not the primary interface.