MOSS-TTSD

MOSS-TTSD TTS

A 7B dialogue model that continues conversations from an audio prompt — up to five speakers and 60 minutes of coherent audio.

Daftar untuk batas 5,000 karakter

Bungkus teks Anda dalam tag SSML untuk kendali yang tepat:

<speak><prosody rate="slow">Slow speech</prosody></speak>

Tag yang dipilih mengerti klik °C untuk memasukkan satu ke dalam teks Anda di mana hal itu terjadi:

Model ini membaca teks biasa, sehingga tag inline diabaikan. Untuk tag berbasis emosi, beralih ke model ekspresif seperti Orpheus atau Bark.

Definisikan pengucapan ubahan (kata = pelafalan):

-12 +12
0.5x 2.0x
Free with Piper, VITS, Melotts
Audio yang Anda buat akan muncul di sini. Pilih model, masukkan teks, dan klik Generate.
Hasil Audio Berhasil
0:00
Unduh Audio Unduh.srt Sambungan berakhir dalam 24 jam
Tingkatan bebas: penggunaan pribadi. Ijin komersial dari $5/mo
Buatlah ini suara Anda sendiri Kloning suara dalam 30 detik
Beritahu teman-temanmu!

Tentang MOSS-TTSD

MOSS-TTSD v1.0 from OpenMOSS is a 7-billion-parameter dialogue text-to-speech model that continues a conversation from a short audio prompt rather than reading isolated lines. It handles up to five simultaneous speakers via [S1]/[S2]-style tags, zero-shot voice cloning from 3-to-10-second references, and stretches of coherent multi-turn dialogue up to 60 minutes long. It is distinct from the OpenMOSS MOSS-TTS model — the TTSD variant is specialized for podcast, audiobook, and dubbing workflows where long, consistent conversational audio is the goal. Released under Apache 2.0, it needs around 12GB of VRAM given its size.

Terbaik untuk: Podcasts, audiobooks, dubbed dialogue, conversational content with multiple voices

Jelajahi semua MOSS-TTSD suara

Pada sekilas

Pengembang
OpenMOSS
Lisensi
Apache 2.0
Tier
standard
Kecepatan
medium
Penklonan Suara
Ya
Bahasa
English, Chinese
Karakter maksimal
5000

MOSS-TTSD suara

Default (Chinese)

Chinese
Standar Neutral

Default Speaker

English
Standar Neutral

MOSS-TTSD TTS °F FAQ

Up to five simultaneous speakers, addressed via speaker tags like [S1] and [S2], with the ability to clone each voice from a short reference clip.

It can produce up to 60 minutes of coherent multi-turn dialogue, which is what makes it suited to full podcast episodes and audiobook chapters rather than short clips.

MOSS-TTSD is a dialogue-specialized variant that continues conversations from an audio prompt and targets podcast, audiobook, and dubbing workflows, whereas the base MOSS-TTS is a general single-voice synthesis model.
← Semua suara