Parler TTS

Parler TTS TTS

Describe the voice you want in plain English and Parler generates speech matching that description.

Aliĝi for 5, 000 character limit

Envolvu vian tekston en SSML- etikedojn por preciza kontrolo:

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

Etikedoj kiujn la elektita modelo komprenas - klaku por meti unu en vian tekston kie ĝi okazas:

This model reads plain text, so inline tags are ignored. For tag-based emotion, switch to an expressive model like Orpheus or Bark.

Difini proprajn elparolojn (vorto = elparolo):

-12 +12
0.5x 2.0x
Libera kun Piper, VITS, MeloTTS
Via generita sono aperos tie ĉi. Elektu modelon, entajpu tekston, kaj alklaku Generi.
Sondosiero sukcese generita
0:00
Elŝuti sonon Elŝuti.srt Ligo eksvalidiĝas post 24 horoj
Libera programaro: persona uzo. Komerca licenco ekde $5/mo
Ĉu vi ŝatas TTS.ai? Diru al viaj amikoj!

Pri Parler TTS

Parler TTS, developed by Hugging Face, replaces voice presets with natural-language control: instead of picking from a fixed list, you write a description such as "a warm female voice with a slight British accent, speaking slowly and clearly," and the model synthesizes speech to match. This makes it unusually flexible for creative work where you need a specific, custom voice character without recording or cloning anyone. It is an 880M-parameter transformer encoder-decoder trained on roughly 45,000 hours of speech, and it is released under the permissive Apache 2.0 license. Parler is English-focused and best suited to applications that benefit from on-demand, describable voice characteristics.

Plej bona por: Creative applications where you need custom voice characteristics

Foliumi ĉiujn Parler TTS voĉoj

Unu rigardo

Programisto
Hugging Face
Licenco
Apache 2.0
Tamuz
standard
Rapideco
medium
Voĉo- klonado
Ne
Lingvoj
English
Maksimuma nombro da signoj
500

Parler TTS voĉoj

Default

English
Defaŭlta Neutral

Parler TTS TTS - FAQ

You describe it in natural language — gender, accent, pace, tone, and recording quality — and Parler generates speech matching the description. There are no preset voices to choose from.

Hugging Face. It is an 880M-parameter transformer encoder-decoder trained on around 45,000 hours of speech and released under Apache 2.0.

No. Parler generates a voice from a text description rather than from a reference recording. For cloning a specific voice, use a model like Chatterbox or GPT-SoVITS.
← Ĉiuj voĉoj