Kutafsiriwa kwa huru kwa Kiyoruba
Trekta ya habari ya Kiyoruba na video kwa kutumia maandishi ya AI.
Jinsi Inavyofanya Kazi
- Nenda Kwenye Free.ai Transcriber
- Pakua kanda yako ya Kiyoruba au faili ya video
- AI yetu hutambua kwa njia ya moja kwa moja Kiyoruba na kuinakili
- Pakua nakala zako zikiwa maandishi au maandishi madogo - madogo ya SRT
Sehemu Zenye Kubadilishana za Kiyoruba
- ✓Uwezo wa BARUA0 (MIT)
- ✓Ugunduzi wa lugha ya Automatic Kiyoruba
- ✓Waunga mkono wabunge3, WAV, MP4, M4A, FARAC, na wengine wengi
- ✓Vipanga vya kusafiri nje ya nchi na sehemu ndogo za nchi hiyo (SRT)
- ✓Hakuna sheria za ukubwa wa faili juu ya mipango ya malipo
- ✓Mafaili ya kibinafsi na salama; faili hufutwa baada ya kukaguliwa
Maelezo ya Lugha
| Lugha | Kiyoruba |
| MELEKEO | yo |
| Gari la Kuigwa | KUBUMISHA |
| Bei | Huru |
Lugha Zaidi
Ona Lugha ZoteFAQ
Kiyoruba is a less-resourced language for Whisper - large-v3-turbo sits above 25% word error rate, sometimes well above. The transcript is useful for search and gist but should not be treated as publication-ready. If a higher-accuracy engine becomes available for Kiyoruba we wire it in automatically.(Tier D, over 25% word error rate kwenye safu za kuwekewa alama - tunachapisha safu za WER zilizonyooka badala ya madai ya mauzo.)
Yes - Kiyoruba transcription draws from your daily free token pool first. Audio costs about 50 tokens per minute, so the anonymous daily pool covers a few hours of audio per day. Signed-in accounts get a larger 30,000-token daily pool. Past that, transcription is pay-as-you-go, with token top-ups from $1.
Picha za Kiyoruba hurudishwa kwa kiwango cha kawaida cha UTF-8 kwa kutumia tethography ya kawaida ya lugha hiyo.
MP3, WAV, M4A, FLAC, OGG, OPUS, and WEBM are accepted directly. For video (MP4, MOV, MKV) we extract the audio track server-side before sending it to Whisper - you do not need to convert anything yourself. Same pipeline regardless of source language, including Kiyoruba.
Anonymous uploads cap at roughly 500 MB per file. Signed-in accounts go up to 2 GB. Duration is not a hard limit - long files are chunked automatically (30-second windows with overlap) and stitched back into a single transcript with continuous timestamps. Multi-hour Kiyoruba recordings (podcasts, full lectures, meetings) work fine.
Naam - msemaji diarifition inaendelea kwa kutolipa gharama ya kila nakala ya Kiyoruba. Utoaji unadaiwa kuwa Mnenaji 1 / Spika 2 / Spika 3 kwa kutumia vipamwi, kwa hiyo mahojiano, majadiliano ya jopo, na mikutano ya sehemu nyingi inarudi ikiwa na alama ya utambulisho.
Yes - paste the URL into /transcribe/youtube/ for YouTube or /transcribe/podcast/ for podcast feeds (Apple, Spotify, RSS). We download the audio, run it through Whisper with language=yo, and return the transcript with timestamps and speaker labels. Typical Kiyoruba content: Maudhui, mahojiano, sauti, na maudhui ya YouTube katika Kiyoruba yote yanafanya kazi - mchanganyiko wa mchanganyiko wa udi/uyotube/utanda au upakiaji wa faili moja kwa moja.
Whisper costs about 50 tokens per minute of audio, so a one-hour recording is ~3,000 tokens. Most users never spend anything - the free daily pool of 30,000 tokens covers short clips, voice notes, and one-off podcasts. Beyond it, transcription is pay-as-you-go, with token top-ups from $1.
Yes - both segment-level (every ~10-30 seconds) and word-level timestamps are available. Word-level is the default for VTT/SRT subtitle export so the captions sync line-by-line. On the API set timestamps="word" in the request body. Picha za Kiyoruba hurudishwa kwa kiwango cha kawaida cha UTF-8 kwa kutumia tethography ya kawaida ya lugha hiyo.
Yes. POST audio (multipart/form-data, field name "file") to /v1/transcribe/ with language=yo - or omit the language parameter to let Whisper auto-detect. Returns JSON with the transcript, segments, timestamps, and speaker labels. Full reference and SDK snippets at /api/.
Yes - once transcription finishes, click Translate or paste the text into /translate/. Kiyoruba pairs with every other language we support (200+). For meeting minutes pipe the transcript through /summarize/; for dubbing send it to /voice/tts/ to render audio in the target language.
Whisper's noise training helps less at this tier - the bottleneck is the amount of Kiyoruba audio Whisper saw during training, not noise. Clean studio audio still beats noisy audio, but neither will reach the accuracy you would get on a high-resource language. If a transcript comes back unusable, email contact@free.ai with the file - we will refund the tokens and look at whether a different engine handles your audio better.