Umbhalo usuka kumazwi Ama-AI Agents Umculo Umsindo kuya kumbhalo Ukulungiswa kwezwi Uhlelo lwezwi Imakethe Okuningi
VoxCPM

Default

Iphutha isiNgisi Neutral VoxCPM

{igama} yizwi le- neutral AI elisebenza ngemodeli ye-VoxCPM yombhalo-kuya-kwezwi. Lezwi le-izinga elijwayelekile likhuluma {ulwimi} futhi linikeza ukuhlanganisa kwezwi le-istudio-quality. Nge i-near-instant isivinini sokukhishwa kanye nezinga lomgangatho lwe 5/5, Default lilungele high-fidelity audio, audiobooks, long-form content with voice consistency. Injini VoxCPM ithuthukiswe ngu OpenBMB under the Apache 2.0 license, iyenza iphephile ukusetshenziswa kwezokuhweba. Izinsiza ezibalulekile zifaka: {izici}. Imodeli VoxCPM isekela futhi ukuklonya kwezwi — ukufaka isampula lomsindo omncane ukwenza izwi elijwayelekile eligcina izici zobuningi ezifanayo.

Akukho manani
Zama lo msindo Zonke VoxCPM Izizwi

VoxCPMUlwazi lwemodeli

Imodeli VoxCPM
Umthuthukisi OpenBMB
Ubunjani
Isivinini Isheshayo
Ilayisense Apache 2.0
Ukuklonya Kuxhaswe
I-Tiger Ijwayelekile (izimpawu ezingu-2x)
Amapharamitha 500M
Ukwakhiwa Continuous Space + Flow Matching
Ulwazi lokuzivocavoca 1800000 amahora
Unyaka 2025

Isibonelo esihle kakhulu sokusetshenziswa Default

Izisebenziso ezivunyelwe ezisekelwe ezici zalesi sizwi

Incwadi yomsindo nenkulumo

Sebenzisa i-Default ukuchaza okuqukethwe kwefomu elide nge-prosody ne-expression ezijwayelekile.

Amavidiyo akhuluma ngazo

Engeza ukukhuluma okusezingeni eliphakeme ku-YouTube amavidiyo, izikhangiso, kanye nesihloko semidiya yomphakathi.

Izicelo & Ukufinyeleleka

Ukukhiqizwa okukhawulelwe kwenza lo msindo ulungele izicelo zesikhathi sangempela, abafundi besiga-nyezi, namathuluzi ofinyeleleka.

I-podcast ne-broadcast

I-study-quality output efanele amapodcast, umsakazo, kanye nokusakazwa okusezingeni eliphakeme.

Okuningi VoxCPM Izizwi

Okunye amagama emodeli efanayo ye-TTS

Default Chinese

isi-Chinese (kunzima) Neutral
Bona konke VoxCPM Izizwi

Imibuzo ebuzwa kaningi

VoxCPM 1.5 ngu OpenBMB yimodeli entsha ye-TTS engena-i-tokenizer esebenza endaweni eqhubekayo ngaphezu kwe-token ehlukile. Ikhiqiza umsindo osezingeni eliphezulu we-44.1kHz, ixhasa ukuklonywa kwezwi elingekho-i-shot kusuka kumasekondi angama-3-10, futhi igcina ukuhambisana phakathi kwamapharamitha. Ukuklonywa kwe-cross-language kuvumela ukuthi usebenzise umsindo wase-English ku-Chinese speech futhi vice versa.

VoxCPM yathuthukiswa yi-OpenBMB futhi ikhishwa ngaphansi kwelayisense le-Apache 2.0, evumela ukusetshenziswa kokuthengiswa kwesandi esikhiqizwe.

VoxCPM isekela ulwimi olulodwa: isiNgisi, isiChinese.

VoxCPM ikwizinga elijwayelekile — ama-credits ama-2 ngamagama angama-1,000. Ungabona kuqala noma yiluphi ubizo lweVoxCPM mahhala ngaphambi kokwenza umsindo ophelele.

VoxCPM inejubane lokuzaliseka elisheshayo kakhulu. Isebenza ngesikhathi esifanayo, iyenza ilungele ukusakazwa kanye nezicelo ezixhumene.

VoxCPM ilinganiselwe 5/5 ngekhwalithi yomsindo ku-TTS.ai. Inikeza isiqophi-se-studio, isikhulumi esifana nomuntu.

Yebo, iVoxCPM isekela ukuklonywa kwezwi elisha. Layisha phezulu imizuzwana engu-5-30 yezwi lokubhekisa ukuze udale ulwimi oluthile.

Yebo, iVoxCPM ikhuthazwa ngokukhethekile kuma-audio aphezulu, ama-audiobooks, izithameli ezide ezinama-voice consistency. I-44.1khz audio, i-tokenizer-free, i-cross-language cloning capabilities yenza kube ngcono kakhulu ukusebenzisa le nkinga.

Yebo, iVoxCPM ivunyelwe ngaphansi kwe-Apache 2.0, evumela ukusetshenziswa kokuthengiswayo. Umsindo okhiqizwa ngemisindo yeVoxCPM ingasetshenziswa kumavidiyo, kumapodcast, kuma-apps, kuma-games, nakwezinye izinhloso zokuthengiswayo.

Yebo, wonke amazwi ku-TTS.ai asebenzisa amamodeli avulekile avunyelwe ngokuhweba (MIT, Apache 2.0). Umsindo okhiqizwe ukhona wena ukuwusebenzisa kumavidiyo, amapodcast, ama-apps, imidlalo, nanoma iyiphi enye inqubo yokuhweba.

Thumela isicelo se-POST ku /api/v1/tts/ ngegama lemodeli ne-ID yomsindo. Bona ikhasi lethu le-API Documentation ngemiboniso yekhodi ku-Python, JavaScript, Go, ne-cURL.

Yebo, chofoza inkinobho yokudlala kulekhasi ukuze ulalele isibonisi. Ungabhala futhi umbhalo ojwayelekile kwikhasi le-Text to Speech futhi udale ukubuka kuqala okumahhala nganoma iyiphi ingoma.

Zama Default Manje

Bhala noma yiluphi uxhumanisi bese ukhuluma ngaso Default. Imahhala ukuyisebenzisa.

Dala ulwimi Ubhalise