Iimodeli ze-AI
Sidibanisa imodeli elungileyo ye-AI yokuthetha-thethana evulekileyo. Zonke imodeli zifumaneka nge-API kunye nothungelwano lwewebhu.
Iimodeli zombhalo-ukuthetha
Chatterbox
Iinketho zendawoUhlobo lwesandi olunombala omnyama omnyama ovela kwisampuli efutshane yobhekiso, kwiilwimi ezili-23. Imodeli yethu emiselweyo yokuluka, ilizwi kwi-AI elibambisayo, nemodeli yethu emiselweyo yokuguqula ilizwi (Chatterbox VC).
I-Kokoro, i-Piper, i-VITS ne-Bark
Four open text to speech engines behind one voice picker. Kokoro 82M (Apache 2.0) is the default; Piper offers only voices whose training data allows commercial use; VITS adds 109 English speakers and Bark 130 presets in 13 languages.
OpenVoice v2
Umbala wokuguqulela umbala kunye nemodeli yokukrola. Iyakhethwa ukuguqula ilizwi, apho iChatterbox VC ngoku imiselwe kuba igcina ngaphezu kwelizwi elibekiweyo.
Uthelekiso lomculi wokulinganisa okuguqulweyo kokulinganisa okuguqulweyo kumfanekiso ongumqondiso ohlukileyo womculi omiselweyo. Iividiyo ezimbini zomculi ofanayo wenyaniso zifumana inqaku le-0.76 ukuya kwi-0.88.
Iimodeli zokuthetha- ukuya- kumbhalo
Whisper Large v3
Esetyenziswa kakhuluI-OpenAI's open-source speech recognition model. Iguqula iilwimi ezili-100, ngee-timestamps nobuchwephesha obuzenzekelayo bokukhangela iilwimi.
Whisper Large v3 Turbo
Uhlobo oluncinci, olukhawulezayo lwe Whisper Large v3 olunokuguqulelwa ngokukhawuleza. Khetha njenge whisper- turbo.
Imodeli yencoko yelizwi
Qwen2.5 7B Instruct
Imodeli yoLwimi oluvulekileyo olubhaliweyo kwincoko yelizwi, kwipersona okhethayo. Umkhangeli zincwadi wakho uguqula uthetha kwakho kwaye ulizwi le Piper lifunda impendulo ngokunzulu.