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.

Înscrie-te pentru limitele de 5000 de caractere

Întoarceți textul în etichetele SSML pentru un control precis:

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

Etichetele modelului selectat înțeleg — click pentru a lăsa unul în textul tău unde se întâmplă:

Acest model citește textul simplu, astfel încât etichetele inline sunt ignorate. Pentru emoții bazate pe tag, schimbați la un model expresiv cum ar fi Orpheus sau Bark.

Definiți pronunțiare personalizată (cuvânt = pronunție):

-12 +12
0.5x 2.0x
Gratuit cu Piper, VITS, MeloTTS
Audio generat va apărea aici. Alegeți un model, introduceți text și faceți clic pe Generați.
Audio generat cu succes
0:00
Descarcă audio Descărcare.srt Legătura expiră în 24 ore
Gratuit: utilizare personală. Licență comercială de la 5$/mo
Spune-i prietenilor tăi!

Despre 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.

Cel mai bun pentru: Podcasts, audiobooks, dubbed dialogue, conversational content with multiple voices

Navigați toate MOSS-TTSD voci

La o privire

Dezvoltator
OpenMOSS
Licență
Apache 2.0
Nivel
standard
Viteză
medium
Clonarea vocală
Da.
Limbi
English, Chinese
Caractere maxime
5000

MOSS-TTSD voci

Default (Chinese)

Chinese
Standard Neutral

Default Speaker

English
Standard Neutral

MOSS-TTSD TTS – 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.
← Toate vocile