StyleTTS 2

Default

Ixabiso eliphezulu IsiNgesi Neutral StyleTTS 2

{igama} yi neutral AI yelizwi elinamandla eStyleTTS 2 umbhalo-kwi-speech model. Eli premium-level ilizwi lithetha IsiNgesi kwaye linika studio-quality speech synthesis. Nge phezulu unikezelo lwesantya kunye nomgangatho womgangatho we 5/5, Default ulungele studio-quality single-speaker synthesis, professional narration. I-StyleTTS 2 injini iphuhliswe ngu Columbia University under the MIT license, iyenza ikhuseleke kwimisebenzi yentengiso. Iinkqubo eziphambili ziquka: {iimpawu}.

Akukho manqaku

StyleTTS 2Ulwazi lwemodeli

Imodeli StyleTTS 2
Umbhekisi phambili Columbia University
Umgangatho
Isantya I-Media
Ilayisensi MIT
Ukuklona Ayifumaneki
I-Tier Ixabiso eliphezulu (4 amakhadi/1K amalungu)
Iiparamitha 100M
Uyilo lwezindlu Style Diffusion + Adversarial Training
Uqeqesho lwe Data 585 iiyure
Iminyaka 2024

Iinkqubo ezilungileyo zokusetyenziswa Default

Iinkqubo ezicetyiswayo ezisekelwe kwiimpawu zalo msindo

Iincwadi ezinesandi & Uxwebhu

Sebenzisa i {igama} ukuchaza imixholo yefom ende nge-prosody eqhelekileyo ne-expression.

Ividiyo

Yongeza ukuthetha okuzimeleyo kwiividiyo zeYouTube, iintengiso, kunye nemixholo yemidiya yoluntu.

Ipodcasts & Ukusasazwa

Imveliso elungileyo yestudio elungele iipodcasts, umculo, kunye nokusasazwa okuzimeleyo.

Imidlalo & Imidiya Esebenza ngokuZenzekelayo

Umgangatho ophezulu wonxibelelwano lwemidlalo, iintsomi ezisebenza kunye, kunye neempendulo ezimdaka.

Imibuzo ebuzwa rhoqo

I-StyleTTS 2 ifumana uxinzelelo lwe-TTS lomgangatho womntu ngokudibanisa ukusasazeka kwesicwangciso kunye noqeqesho oluchaseneyo lusebenzisa iimodeli ezinkulu zesivakalisi. Ivelisa isivakalisi esidlangalaleni phakathi kweemodeli zomthumeli omnye, esinokhuphisana neengxelo zomntu. I-StyleTTS 2 isebenzisa ukusasazeka-okusekelwe kuyilo lwesivakalisi ukutsala uluhlu olupheleleyo lotshintsho lwesivakalisi somntu.

I-StyleTTS 2 yaphuhliswa yi-Columbia University kwaye ikhutshwe phantsi kwelayisensi ye-MIT, evumela ukusetyenziswa korhwebo lwesandi esiveliswe.

StyleTTS 2 inkxaso 1 ulwimi: isiNgesi.

I-StyleTTS 2 ikwinqanaba eliphezulu — ii-credits ezi-4 ngabasebenzi aba-1,000. Ungajonga ngaphambili nayiphi na i-StyleTTS 2 yesandi ngaphandle kokuvelisa isandi esipheleleyo.

I StyleTTS 2 inesantya sokwakha esiphakathi. Ukwakha kuthatha imizuzwana emibini exhomekeke kubude bombhalo.

I-StyleTTS 2 ifunyenwe 5/5 kwi-audio quality kwi-TTS.ai. Inikezela nge-studio-grade, ukuthetha okunjalo nomuntu.

Hayi, i-StyleTTS 2 isebenzisa iseti emiselweyo yelizwi elingaphakathi. Ukuphinda usebenzise ilizwi, zama iimodeli ezinjenge-CosyVoice 2, GPT-SoVITS, okanye i-Chatterbox.

Ewe, i StyleTTS 2 icetyiswa ngokukodwa kwi studio- umgangatho wesandi esifanayo, ukuthetha okuzimeleyo. Inqanaba layo lomuntu, ukusasazeka kwendlela, uqeqesho oluchaseneyo luyenza ibe yinketho elungileyo kule meko yokusetyenziswa.

Ewe, i-StyleTTS 2 ilayisensiwe phantsi kwe-MIT, evumela ukusetyenziswa korhwebo. Isandi esiveliswe nge-StyleTTS 2 ilizwi lingasetyenziswa kwividiyo, iipodcasts, iinkqubo, imidlalo, nakweyiphi na enye iprojekthi yorhwebo.

Ewe, zonke iingoma kwi-TTS.ai zisebenzisa iimodyuli ze-open-source ezilayisensiweyo ngentengiso (MIT, Apache 2.0). Isandi esiveliswe yiyo yakho ukuyisebenzisa kwividiyo, iipodcasts, iiapps, imidlalo, nakweyiphi na enye inkqubo yentengiso.

Thumela isicelo se POST ku /api/v1/tts/ ngegama lemodeli ne ID yesandi. Bona iphepha lethu le-API Documentation ngemizekelo yekhowudi kwi-Python, JavaScript, Go, kunye ne-cURL.

Ewe, nqakraza iqhosha lokudlala kweli phepha ukuva isampuli. Ungabhala umbhalo oqhelekileyo kwiphepha lombhalo ukuya kukuthetha kwaye wenze ukujonga kuqala simahla ngelizwi elithile.

Zama Default Ngoku

Bhala nawuphi na umbhalo uze uyiva ithetha ngu Default. Ifumaneka simahla.