Moonshine Base
Free.ai (self-hosted)
·
stt
·
~500 tokens per minute
Moonshine Base is a kutaura-ku-tebhu model built by Useful Sensors. Strongest at Low-latency live transcription, embedded devices.. Self-inotarisirwa pa Free.ai GPUs - inofamba zvakasununguka pazuva rako re token pool (500 tokens per minute). Yakaburitswa pasi pe MIT — 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/stt/ \
-H "Authorization: Bearer sk-free-..." \
-H "Content-Type: application/json" \
-d '{"model":"moonshine-base","audio_url":"https://..."}'Zvimwe zvinobvunzwa kakawanda
Moonshine Base inoshandura mashoko akataurwa kuita mashoko. Upload a MP3, WAV, M4A, kana video file and Moonshine Base returns the full transcript plus optional SRT/VTT subtitles with timestamps.
Moonshine Base 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.
Moonshine Base inofamba paGPU yedu yedu yezuva nezuva yemahara pool yekutanga; $ 5 → 200,000 yakabhadharwa ma tokens mushure meizvozvo.
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/. Moonshine Base 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="Moonshine Base". 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.