Model Overview

Mossland platform speech models fall into two capability categories: speech generation and speech recognition. Click any model card to open its details on the right.

Speech Generation

MOSS-TTS-v1.5-FlashSingle-speaker text-to-speech modelMOSS-TTS-v1.0-ProSingle-speaker text-to-speech modelMOSS-TTSDMulti-speaker dialogue speech synthesis modelMOSS-VoiceGeneratorGenerate speech from text and voice instructions

Speech Recognition

MOSS-TranscribeGeneral audio transcription modelMOSS-Transcribe-Diarize-ProMulti-speaker transcription model