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

Speaker 3

Iphutha isiNgisi Neutral VibeVoice

{igama} yizwi le- neutral AI elisebenza ngemodeli ye-VibeVoice 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, Speaker 3 lilungele podcasts, dialogues, long-form narration, multi-speaker content. Injini VibeVoice ithuthukiswe ngu Microsoft under the MIT license, iyenza iphephile ukusetshenziswa kwezokuhweba. Izinsiza ezibalulekile zifaka: {izici}.

Akukho manani
Zama lo msindo Zonke VibeVoice Izizwi

VibeVoiceUlwazi lwemodeli

Imodeli VibeVoice
Umthuthukisi Microsoft
Ubunjani
Isivinini Isheshayo
Ilayisense MIT
Ukuklonya Ayikho
I-Tiger Ijwayelekile (izimpawu ezingu-2x)
Amapharamitha 1.5B
Ukwakhiwa LLM + DAC
Ulwazi lokuzivocavoca 100000 amahora
Unyaka 2025

Isibonelo esihle kakhulu sokusetshenziswa Speaker 3

Izisebenziso ezivunyelwe ezisekelwe ezici zalesi sizwi

Incwadi yomsindo nenkulumo

Sebenzisa i-Speaker 3 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 VibeVoice Izizwi

Okunye amagama emodeli efanayo ye-TTS

Speaker 1

isiNgisi Neutral

Speaker 1 (Chinese)

isi-Chinese (kunzima) Neutral

Speaker 2

isiNgisi Neutral

Speaker 2 (Chinese)

isi-Chinese (kunzima) Neutral

Speaker 4

isiNgisi Neutral
Bona konke VibeVoice Izizwi

Imibuzo ebuzwa kaningi

VibeVoice nguMicrosoft ivela ngezigaba ezimbili: imodeli engu-1.5B yezinto ezinombhalo ophakathi (imizuzu engu-90, abakhulumayo abangu-4) kanye nemodeli engu-Realtime 0.5B yokusakaza nge-~200ms yokuqala yobuciko besandi. I-1.5B ivelele kumapodcasts nama-audiobooks ngobuciko besandi obungalingani ngaphezu kwezigaba ezide. Qaphela: Microsoft isuse ikhowudi ye-TTS kusuka ebhokisini lokugcinwa futhi ikhiqize umsindo ofaka phakathi ukukhishwa kwe-AI okuzwakalayo.

I-VibeVoice yathuthukiswa yi-Microsoft futhi ikhishwa ngaphansi kwelayisense le-MIT (ucwaningo kuphela), evumela ukusetshenziswa kokuthengiswa kwesandi esikhiqizwe.

I-VibeVoice isekela ulwimi 1: isiNgisi.

I-VibeVoice ikwi-Premium level — ama-credits angu-4 ngamagama angu-1,000. Ungabona kuqala noma yiluphi izwi le-VibeVoice mahhala ngaphambi kokwenza umsindo ophelele.

I-VibeVoice inejubane lokuzaliseka eliphakathi. Uzaliseka kuthatha imizuzwana emincane ngokuya ngedekhi yombhalo.

I-VibeVoice ilinganiselwe 5/5 ngekhwalithi yomsindo ku-TTS.ai. Inikeza ukukhuluma okufana ne-studio.

Hayi, i-VibeVoice isebenzisa isiqephu esiqinile samazwi afakwe ngaphakathi. Ukwenza isikhalazo, zama amamodeli afana ne-CosyVoice 2, GPT-SoVITS, noma ibhokisi lokuxoxa.

Yebo, iVibeVoice ikhuthazwa ngokukhethekile kumapodcast, ama-audiobooks, izithameli eziningi ezinomsindo ezinomsindo. Izithameli eziningi, kuze kube yi-90 min, ikhono lokuthuthukisa amapodcast kwenza kube ngcono kakhulu ukusebenzisa le nkinga.

Yebo, i-VibeVoice ivunyelwe ngaphansi kwe-MIT (ucwaningo kuphela), okuvumela ukusetshenziswa kokuthengiswayo. Umsindo okhiqizwa ngemisindo ye-VibeVoice ungasetshenziswa 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 Speaker 3 Manje

Bhala noma yiluphi uxhumanisi bese ukhuluma ngaso Speaker 3. Imahhala ukuyisebenzisa.

Dala ulwimi Ubhalise