Fal Speech-to-Text
Free.ai
·
stt
·
~500 tokens per minute
Fal Speech-to-Text is a kutaura-ku-tebhu model. Kuendeswa kuburikidza kunze mamodheru — ~ 500 tokens per minute (50% markup pamusoro upstream mutengo).
Usati washandisa
OpenAI-compatible REST API. Generate a key and call this model in seconds.
curl -X POST https://api.free.ai/v1/stt/ \
-H "Authorization: Bearer sk-free-..." \
-H "Content-Type: application/json" \
-d '{"model":"premium/speech-to-text","audio_url":"https://..."}'Zvimwe zvinobvunzwa kakawanda
Fal Speech-to-Text inoshandura mashoko akataurwa kuita mashoko. Upload a MP3, WAV, M4A, kana video file and Fal Speech-to-Text returns the full transcript plus optional SRT/VTT subtitles with timestamps.
Fal Speech-to-Text inobata mazhinji ematauro — Whisper-family models inobata 90+, Parakeet inobata ~25, vamwe vari. Choose "auto-detect" or specify the language for highest accuracy.
Word-kukanganisa rate iri 5-10% patsva English audio, 10-20% patsva noiseful kana accented audio. Large zviuru zveimwe architecture kuita zvakakwana zvakanaka pazvikonzero zvakaoma — pick makuru apo audio iri rough.
Yeah - chero segment inosanganisira kutanga / kupera timestamps. Export se SRT kana VTT uye nguva map rakananga pane yako video.
Fal Speech-to-Text inyanzvi yekunyora mavhidhiyo. Panguva ino, Fal Speech-to-Text inonyora ~500-1,500 tokens pamin. yevhidhiyo. $1 = 750,000 tokens.
MP3, WAV, M4A, FLAC, OGG, plus video (MP4, MOV, WebM) — isu tinotora audio. Max 500 MB per upload. Longer files? Split with /audio/cut/ or use /v1/stt/batch/.
Speaker diarization imwechete chete — toggle "diarize" on /transcribe/. Fal Speech-to-Text inodzora kushandurwa; diarization inoisa mazita evanhu vari muchikamu chimwe nechimwe nezita remunyori 1 / munyori 2 / etc.
Yeah — /batch/ inogamuchira folder ye audio files. Each transcript lands in /account/?tab=history with the original filename. For folder-tree preservation use the API.
Yes — POST your audio to /v1/stt/transcribe/ with model="Fal Speech-to-Text". Returns JSON with text + segments + word-level timestamps. /api/ has the full reference.
Self-hosted mamodheru kuchengetedza audio paGPU yedu; premium kutevedzera ne DPA. Audio inofanira kugadziriswa mushure mekugovera-window (24h ano, 7d signed-in). Ticharamba kudzidza kubva kune yako input.
Yes — Free.ai grants commercial use of transcripts. You need rights to the audio you uploaded (your own recording, licensed material, or content with consent).
Real-nguva chikamu ndechinenge 0.05-0.2 × — 60-minute podcast transcribes mu 3-12 maminitsi. Premium mamodheru kazhinji kupera nekukurumidza.