Distil-Whisper large-v3
Free.ai (self-hosted)
·
stt
·
~500 mabao kwa kila mmoja minute
Distil-Whisper large-v3 nia Picha ya mfano inayotokana na maneno na habari iliyojengwa na HuggingFace. Wenye nguvu zaidi katika Real-time transcription, large-volume batch STT.. Self-hosted on Free.ai GPUs — runs free against your daily token pool (500 tokens kwa dakika moja). Utumizi wa kibiashara ulioruhusiwa kwa MIT uliachiliwa chini ya Free.ai.
Tumia kupitia API
MFUMO wa chembe za urithi wenye uwezo sawa API. Generate ni ufunguo na kwa sekunde chache unaita kiolezo hiki.
curl -X POST https://api.free.ai/v1/stt/ \
-H "Authorization: Bearer sk-free-..." \
-H "Content-Type: application/json" \
-d '{"model":"distil-whisper-large-v3","audio_url":"https://..."}'Maswali Ambayo Watu Huuliza Mara Nyingi
Distil-Whisper large-v3 transcribes spoken audio into text. Upload an MP3, WAV, M4A, or video file and Distil-Whisper large-v3 returns the full transcript plus optional SRT/VTT subtitles with timestamps.
Distil-Whisper large-v3 handles dozens of languages - Whisper-family models cover 90+, others vary. Pick "auto-detect" or specify the language for highest accuracy.
Kiwango cha maneno ni 5-10% kwenye sauti safi ya Kiingereza, asilimia 10-20 kwenye sauti ya sauti ya kelele au ya matamshi.
Ndiyo - kila sehemu inajumuisha kuanza na mwisho vipindi vya kukatuka. Export kama SRT au VT na ramani mara moja kwenye video yako.
Distil-Whisper large-v3 runs on our own GPUs against your daily free pool first; $5 → 200,000 paid tokens after that. About ~500 tokens per minute.
MP3, WAV, M4A, NOAC, OG, pamoja na video (MP4, MV, WebM) - tunatoa sauti. Max 500 MB kwa kila sehemu ya juu. Mafaili marefu zaidi? Mafaili hayo yanaambatana na /udio/cuti/umika/v1/julat/batch/.
Maneno ya sauti ni njia tofauti ya kupitisha "kutengeneza" kwenye ukurasa wa kwanza/. Distil-Whisper large-v3 inashika nakala ya nakala; majina ya udishaji hubandikwa kila sehemu kwa kigombani cha 1 / Spika 2 / n.k.
Ndiyo - /batch/lakala ya faili za sauti. Kila nakala ya nchi katika /aclaw/?tabÉethisry kwa jina la awali la faili.
Ndiyo - Tazama sauti yako kwa /v1/strans/with mrengo"Distil-Whisper large-v3". Repens JSON ikiwa na maandishi + calvel vimps. /api/ ina marejezo kamili.
Waigaji wenye ubinafsi huweka sauti kwenye mtandao wetu wa GPUs; huduma za afya hupita kwa kutumia mashine ya DPA.udio hufutwa baada ya jopo la pamoja (24h aon, 7d-in).
Ndiyo - Free.ai hutoa nakala za kibiashara ambazo unahitaji haki za kusikiliza kaseti ulizoweka (rekodi yako mwenyewe, vifaa vilivyoidhinishwa, au kuridhika na idhini).
Real-time factor is roughly 0.05-0.2× - a 60-minute podcast transcribes in 3-12 minutes. Premium models often finish faster. Use the queue button to close the tab.