Tortoise TTS

Tortoise TTS ТТС

A quality-first autoregressive model — slow, but among the most realistic open-source speech available.

Ёзиш 5000 белги чегараси

Матнни аниқ назорат учун SSML теглар билан ўраб қўйиш:

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

Танланган модел тушунадиган тегилар — уларни матнга тушириш учун босинг:

Бу модел оддий матн ўқийди, шунинг учун тегишли теги эътиборга олинмайди. Эмоционал теги асосида, Orpheus ёки Bark каби ифодали моделга ўтинг.

Ўз нутқини белгилаш (сўз = нутқ):

-12 +12
0.5x 2.0x
Piper, VITS, MeloTTS билан бепул
Сизнинг яратилган аудионгиз бу ерда намоён бўлади. Модельни танланг, матнни киритинг ва Юклаш тугмасини босинг.
Аудио муваффақиятли яратилди
0:00
Аудио юклаб олиш .srt юклаб олиш Уланиш муддати 24 соатдан сўнг тугайди
Бепул даража: шахсий фойдаланиш. $5/mo дан бошланувчи коммерциявий лицензия
Буни ўз овозингизга айлантиринг 30 сония ичида овозни клонлаш
TTS.ai'ни севасанми? Дўстларингга айт!

Маълумот Tortoise TTS

Tortoise TTS, created by James Betker, deliberately trades speed for quality. It is an autoregressive multi-voice system using a DALL-E-inspired architecture, and it produces some of the most realistic synthetic speech in the open-source ecosystem, with excellent prosody and speaker similarity. The name is a nod to its pace: it is noticeably slower than most alternatives, but the payoff is studio-grade output. It supports multiple voices and voice cloning (which benefits from a longer reference, around fifteen seconds), making it a long-standing favorite for audiobooks and premium narration where wait time is acceptable. Tortoise is English-focused and released under the permissive Apache 2.0 license.

Энг яхшиси: Audiobooks, premium content, quality-first applications

Ҳаммасини кўриш Tortoise TTS овозлар

Бир қарашда

Ижодкор
James Betker
Лицензия
Apache 2.0
Тир
premium
Тезлик
slow
Овозни клонлаш
Ҳа
Тиллар
English
Максимум ҳарфлар
2000

Tortoise TTS овозлар

Random

English
Premium Neutral

Tortoise TTS ТТС — кўп бериладиган саволлар

It is autoregressive and uses a DALL-E-inspired architecture that deliberately prioritizes quality over speed. The trade-off is some of the most realistic open-source speech available, which is why it remains popular for audiobooks despite the wait.

Yes. It supports multi-voice synthesis and voice cloning; results improve with a longer reference, around fifteen seconds of clean audio.

Quality-first applications — audiobooks and premium narration — where its slow but highly realistic output is worth the generation time. It is English-focused and Apache 2.0 licensed.
← Барча овозлар