← All models
ElevenLabs: Scribe v2
elevenlabs/scribe-v2transcription
ElevenLabs Scribe v2 is a speech-to-text model that transcribes audio in 90+ languages with word-level timestamps, optional speaker diarization, and audio-event tagging.
Price
Released
Oct 7, 2026
Parameters
fileaudio file (multipart)How to use via API
from openai import OpenAI
client = OpenAI(base_url="https://api.mixen.ai/v1", api_key="mxn-...")
tr = client.audio.transcriptions.create(
model="elevenlabs/scribe-v2",
file=open("audio.mp3", "rb"),
)
print(tr.text)
