Skip to content
models / ElevenLabs / Scribe v3

Scribe v3

audioelevenlabs/scribe-v3

ElevenLabs Scribe v3 is ElevenLabs' most accurate speech recognition model for recorded audio, with 90+ languages, speaker diarization for up to 32 speakers, word-level timestamps, audio event tags, keyterm prompting, numbers as digits or words, and secondary languages for mixed-language audio.

$0.00333list priceper audio minute
pricing
unitlist price
per audio minute$0.00333
per audio minute (key terms)$0.000833

Everyone pays the list price. What comes back grows with your Reward Status: Noob 0.5% of every spend buys back $INFX, Pro (hold 1,337 $INFX) 2%, Elite (also hold 1,337 $XAVA) 5%. How it works

curl
curl https://xavainf.com/v1/media/generations \
  -H "Authorization: Bearer $XINF_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"elevenlabs/scribe-v3","input":{"text":"Hello from one key."}}'
limits
providerElevenLabs
typeaudio
context window—
max output—
prompt storagenone
provider retentionthe model provider's policy
livesoon
requests 24h—
p50 latency—
uptime 7d—