I-isi-Welsh yokudlulisa
Bhala isi-Welsh umsindo nevidiyo ube ngumbhalo nge-AI. Ishesha, ilungile, futhi imahhala.
Indlela isebenza ngayo
- Iya ku- Umshicileli we-Free.ai
- Layisha phezulu ihele lakho le-isi-Welsh lomsindo noma levidiyo
- I-AI yethu ithola ngokuzenzakalela i-isi-Welsh futhi ibhalela
- Layisha phezulu isingeniso sakho njengesihloko noma isingeniso se-SRT
isi-Welsh Izici zokudlulisa
- ✓Isebenza nge-faster-whisper (MIT licensed)
- ✓Ukuthola ulwimi isi-Welsh ngokuzenzakalela
- ✓Insiza MP3, WAV, MP4, M4A, FLAC, nezinye eziningi
- ✓Isikhathi sokufaka kanye nokukhishwa kwesihloko esingezansi (SRT)
- ✓Akukho mkhawulo wobukhulu befayela kuma-plans akhokhelwayo
- ✓Imfihlo nokuphepha -- amafayela asuswa ngemuva kokusebenza
Iminingwane yesilimi
| I-Language | isi-Welsh |
| Ikhowudi ye-ISO | cy |
| Imodeli ye-AI | i-faster-whisper |
| Intengo | Ikhululekile |
Izilimi Eziningi
Bona zonke izilimiImibuzo ebuzwa kaningi
isi-Welsh yimithombo yesilimi se-Whisper — i-large-v3-turbo iwela ku-15-25% yegama lephutha le-rate band. I-gist ye-transcript ithembekile; cabanga iphutha legama-entity, i-code-switching glitches, ne-short-utterance misfires. Phinda i-human pass for publication-quality output.(I-Tier C, 15-25% word error rate kusethingi se-benchmark — sishicilela ama-tiers we-WER athembekile ngaphezu kokuphikisana nokumaketha.)
Yebo — isi-Welsh ukudluliswa kuqala kusuka ku-token pool yakho yamahhala yansuku zonke. Umsindo ubiza ama-token angama-50 ngomzuzu, ngakho-ke i-pool yansuku zonke engaziwa ifaka amahora ambalwa we-audio ngosuku. Ama-akhawunti abhalisiwe athola i-pool enkulu kanye nama-token angama-10,000 wokubhalisa. Phakathi kwalokhu, i-$1 ithenga ama-token angama-750,000 (amahora angama-250 e-audio).
isi-Welsh izixhumanisi zibuyiselwa ku UTF-8 ejwayelekile nge-ortography ejwayelekile yesilimi.
MP3, WAV, M4A, FLAC, OGG, OPUS, ne WEBM zivunyelwe ngokuqondile. Ngevidiyo (MP4, MOV, MKV) sikhipha umsindo we-server-side ngaphambi kokuthunyelwa ku-Whisper — awudingi ukushintsha noma yini ngokwakho. Ipayipi elifanayo ngaphandle komthombo we-language, kufaka phakathi i-isi-Welsh.
Ukufaka okungenagama kufinyelela kuma-500 MB ngefayela ngalinye. Ama-akhawunti abhalisiwe afinyelela ku-2 GB. Ukuphela kwesikhathi akuyona umkhawulo onzima - amafayela ade ahlukaniswa ngokuzenzakalela (amafasitela emizuzu engu-30 ahlukaniswe) futhi aphinde ahlukaniswe ibe yi-transcript eyodwa nesikhathi esiqhubekayo. Ukurekhodwa kwehora eliningi isi-Welsh (amapodcasts, izifundo ezigcwele, izinhlanganiso) kusebenza kahle.
Yebo — ukudweba umsindo komsindo kusetshenzisiwe ngokuzenzakalela kuwo wonke ama-isi-Welsh transcript. I-output ihlukaniswe njenge-Speaker 1 / Speaker 2 / Speaker 3 nge-timestamps, ngakho-ke izingqungquthela, izingqungquthela zepaneli, nezingqungquthela zeqembu eliningi zibuyela emuva zinikezwe i-label. Ukudweba umsindo kusebenza ngemodeli ehlukile futhi kusebenza ngokufanayo kuwo wonke ama-languages esiwaxhasayo.
Yebo — chofoza i-URL ku /transcribe/youtube/ ye-YouTube noma /transcribe/podcast/ ye-podcast feeds (Apple, Spotify, RSS). Silanda umsindo, siwuqhube nge-Whisper nge-language=cy, futhi sibuyisele i-transcript nge-timestamps ne-speaker labels. I-isi-Welsh ejwayelekile: izifundo, izingqungquthela, izimemo zomsindo, kanye ne-YouTube isi-Welsh zonke zisebenza — chofoza i-URL /transcribe/youtube/ noma ulayishe ifayela ngqo.
I-Whisper ibiza cishe ama-token angama-50 ngomzuzu we-audio, ngakho-ke ukurekhodwa kwehora elinye kubiza ama-token angama-3,000. I-$1 ithenga ama-token angama-750,000, okusebenza cishe amahora angama-250 we-audio ngedola. Abaningi abasebenzisayo abachithanga lutho — i-pool yamahhala yosuku lonke ifaka ama-clip aphansi, ama-notes omsindo, nama-podcasts afanayo.
Yebo — zombili isigaba-sezinga (noma yikuphi ~10-30 imizuzwana) kanye negama-level timestamps zikhona. Igama-level yiphutha le-VTT/SRT subtitle export ngakho ama-captions asynchronize line-by-line. Kwi-API hlela timestamps="word" kwi-body yesicelo. isi-Welsh izixhumanisi zibuyiselwa ku UTF-8 ejwayelekile nge-ortography ejwayelekile yesilimi.
Yebo. POST umsindo (ingxenye/ifomu-data, igama lendawo "ihele") ku /v1/transcribe/ nge lingu=cy — noma ushiye i parameter yesilimi ukuze i Whisper ikwazi ukukhomba ngokuzenzakalela. Ibuyisela i JSON nge lingu, amasegmenti, ama-timestamps, nama-speaker labels. Umbiko ophelele kanye ne-SDK snippets ku /api/.
Yebo — uma ukuguqulelwa kuqediwe, chofoza guqula noma chofoza umbhalo ku /guqula/. isi-Welsh ixhumana nanoma iyiphi enye ulwimi esixhasayo (200+). Usuku lwengxoxo lidlulisa ukuguqulelwa /summarize/; ukuguqulelwa lithunyelwe ku /voice/tts/ ukuze kunikezwe umsindo kulimi oluzosetshenziswa.
Ukwehlukana kwe-noise ye-Whisper kuqhubeka kusebenza ku-isi-Welsh, kodwa kulolu hlobo lokunemba noma yikuphi ukungqubuzana okungeziwe kuhlanganise nezinga lephutha le-baseline. Umsindo we-headset ohlanzekile unikeza izimpendulo ezingcono kakhulu kunefoni noma ukurekhodwa kwe-laptop-mic.Uma i-transcript ibuyela ingasebenzi, thumela i-imeyili ku contact@free.ai ngefayela — sizobuyisela imali ye-token futhi sibheke ukuthi ngabe i-engine eyahlukileyo iphatha umsindo wakho kahle.