SadTalker
Free.ai (self-hosted)
·
video
·
~30000 tokens per video clip
·
3.2
kubva 78 1 mushandisi munyaya ino
SadTalker is a video generation model built by OpenTalker. Strongest at Avatar explainers, voice-over to video, talking-head ads, dubbed content.. Self-inotarisirwa pa Free.ai GPUs - inofamba zvakasununguka pazuva rako re token pool (30,000 tokens per ~5s clip). Yakaburitswa pasi pe Non-commercial (BFM) — kushandiswa kwekutengesa kwakabvumirwa pa Free.ai.
Usati washandisa
OpenAI-inowirirana REST API. Kugadzira chiratidzo uye kukumbira iyi model mumasekondi.
curl -X POST https://api.free.ai/v1/video/generate/ \
-H "Authorization: Bearer sk-free-..." \
-H "Content-Type: application/json" \
-d '{"model":"sadtalker","prompt":"your prompt here"}'Semuenzaniso mamodheru
Zvimwe zvinobvunzwa kakawanda
SadTalker is one of the AI video models available on Free.ai. Usashandisa fomati pane iyi peji kuti uite clip; pasi pefold iwe uchawana mifananidzo, mutengo, uye sarudzo.
Pa Free.ai, video generation tops out at 6 seconds per clip across all video models. To extend, use the Extend button on the full /video/ tool — it captures the last frame and continues from there.
16:9 landscape (YouTube, desktop), 9:16 portrait (TikTok, Reels, Shorts), uye 1:1 square (Instagram feed).Picka iyo ratio mufomu usati wagadzira kuti iyo model iite shot yeiyo shape.
720p HD sezvakajairika. Zvimwe zvemhando yepamusoro zvinotsigira kusvika pa1080p — tarisa pane peji re Compare. Unogona kuchinja-chinja chero kubuda mu /video/upscaler/ mushure mekunge waita izvi.
Kukura kwesimba pakuva nesimba pakuva nesimba pakuva nesimba pakuva nesimba pakuva nesimba pakuva nesimba pakuva nesimba pakuva nesimba pakuva nesimba pakuva nesimba pakuva nesimba pakuva nesimba pakuva nesimba pakuva nesimba pakuva nesimba pakuva nesimba pakuva nesimba pakuva nesimba pakuva nesimba pakuva nesimba pakuva nesimba pakuva nesimba pakuva nesimba pakuva nesimba pakuva nesimba pakuva nesimba pakuva nesimba pakuva nesimba.
Free.ai inokupa iwe kupihwa kwekushandisa kwekutengesa kwevhidhiyo yakagadzirwa, pasina kunyatsotarisa pane chigadzirwa. Chigadzirwa chinogona kunge chiri Apache 2.0, MIT, kana chigadzirwa chemutengesi chaicho. Ona chinongedzo chechigadzirwa pazasi.
SadTalker runs on our own GPUs at 30,000 tokens per clip, flat: a render costs what it costs because of model load and diffusion steps, not clip length, and 2,500 per second only takes over past 12 seconds. That is the entire 30,000-token daily free pool, so a free account gets one clip every two days. Paid token packs start at $5 → 200,000 tokens and remove the cap.
Yeah — shandisa /batch/ kusvika kune 100 maprompts. Kana iwe uchida kuisa imwe clip mubhokisi, shandisa /account/?tab=history.
Yeah — POST yako prompt kuti /v1/video/generate/ with model="SadTalker" (kana kushandisa slug pane iyi peji). Ona /api/ yezvose endpoint reference plus auth, makodhi ematambudziko, uye SDK snippets.
Isu hatichengete mameseji ako kunze kwebhokisi rekugovana (24h ano, 7d akapinda). Isu hatidzidzise pane yako yekupinda. Self-hosted mamodheru anofamba paFree.ai-inopihwa GPUs.
Yeah — kukundikana mabasa anodzoserwa otomatiki kune yazvino kubhadhara chikuva (zuva nezuva pool kana akabhadharwa tokens) mazuva akafanana. Email contact@free.ai kana mari yekudzosera hairatidzike.
Zviri pachena render 30-120 masekondi ye4-sekondi clip; premium mamodheru kazhinji kupera mu 15-45 masekondi. Usati kuvhura-tab-safe queue bhatani pa / video / — yako chikonzero nharaunda mu / account /? tab = history pashure, nesarudzo email.