Dia TTS

Speaker 2

Iphutha isiNgisi Neutral Dia TTS

{igama} yizwi le- neutral AI elisebenza ngemodeli ye-Dia TTS yombhalo-kuya-kwezwi. Lezwi le-izinga elijwayelekile likhuluma {ulwimi} futhi linikeza ukuhlanganisa kwezwi le-istudio-quality. Nge ophakathi isivinini sokukhishwa kanye nezinga lomgangatho lwe 5/5, Speaker 2 lilungele podcasts, audiobook dialogues, conversational content. Injini Dia TTS ithuthukiswe ngu Nari Labs under the Apache 2.0 license, iyenza iphephile ukusetshenziswa kwezokuhweba. Izinsiza ezibalulekile zifaka: {izici}.

Akukho manani

Dia TTSUlwazi lwemodeli

Imodeli Dia TTS
Umthuthukisi Nari Labs
Ubunjani
Isivinini I-Media
Ilayisense Apache 2.0
Ukuklonya Ayikho
I-Tiger Ijwayelekile (izimpawu ezingu-2x)
Amapharamitha 1.6B
Ukwakhiwa Transformer Autoregressive + DAC
Unyaka 2024

Isibonelo esihle kakhulu sokusetshenziswa Speaker 2

Izisebenziso ezivunyelwe ezisekelwe ezici zalesi sizwi

Incwadi yomsindo nenkulumo

Sebenzisa i-Speaker 2 ukuchaza okuqukethwe kwefomu elide nge-prosody ne-expression ezijwayelekile.

Amavidiyo akhuluma ngazo

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

I-podcast ne-broadcast

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

Ukufunda nokufundisa

Dala amathuluzi okuqeqesha, izifundo, kanye nezinto ezifundiswayo ezibandakanya ukukhuluma nge-AI.

Okuningi Dia TTS Izizwi

Okunye amagama emodeli efanayo ye-TTS

Speaker 1

isiNgisi Neutral

Imibuzo ebuzwa kaningi

I-Dia i-Nari Labs iyimodeli ye-1.6B parameter text-to-speech eyenziwe ngokukhethekile ukudala umsindo womsindo oningi. Ingakhiqiza ukuxhumana okubukekayo phakathi kwama-speakers amabili ngokuthatha i-turn-taking, i-prosody, kanye nokubonisana okunengqondo. I-Dia iyilungile ukudala okuqukethwe kwe-podcast-style, umsindo wencwadi yomsindo, kanye ne-AI yokuxhumana.

I-Dia TTS yathuthukiswa yi-Nari Labs futhi yakhishwa ngaphansi kwelayisense le-Apache 2.0, evumela ukusetshenziswa kokuthengiswa kwesandi esikhiqizwe.

I-Dia TTS isekela ulwimi 1: isiNgisi.

I-Dia TTS ikwi-Standard tier — ama-credits angama-2 ngamagama angama-1,000. Ungabona kuqala noma yiluphi ucingo lwe-Dia TTS mahhala ngaphambi kokwenza umsindo ophelele.

I-Dia TTS inejubane lokuzaliseka okuphakathi. Uzaliseka kuthatha imizuzwana emincane ngokuya ngedekhi yombhalo.

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

Hayi, iDia TTS isebenzisa iset eqinile yamazwi afakwe ngaphakathi. Ukwenza umsindo ufana, zama amamodeli afana neCosyVoice 2, GPT-SoVITS, noma i-Chatterbox.

Yebo, iDia TTS ikhuthazwa ngokukhethekile kumapodcast, ama-audiobook dialogues, izithameli zokuxoxa. Isikhulumi sayo esiningi, ukuthuthukiswa kwe-dialog, ukushintshana okujwayelekile kwenza kube ngcono kakhulu ukusebenzisa le nkinga.

Yebo, iDia TTS ilayisense ngaphansi kwe-Apache 2.0, evumela ukusetshenziswa kokuthengiswayo. Umsindo okhiqizwa ngemisindo yeDia TTS 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 Speaker 2 Manje

Bhala noma yiluphi uxhumanisi bese ukhuluma ngaso Speaker 2. Imahhala ukuyisebenzisa.