State-of-the-art batch STT — 90+ languages, speaker diarization, audio tagging
76 languages · benchmarked
Scribe v2 is a speech-to-text model from ElevenLabs. In our standardized benchmarks it reaches 9.15% word error rate, ranking #2 of 35 models tested. It supports 76 languages and runs at $0.004/min — cheaper than most alternatives.
Its nearest benchmarked alternative is Soniox STT (Async). Best suited for multi-speaker conversations, multilingual workloads, accuracy-critical work, and high-volume, cost-sensitive pipelines.
Overall Score
78.2
#2 of 35
Word Error Rate
9.15%
Character Error Rate
7.19%
Match Error Rate
8.51%
Word Info Lost
12.30%
Avg Latency
3.1s
Benchmarks Run
35
last 30 runs
Word error rate
9.15%
↓ 59.8% · 30d
3 runs ago
latest
Avg latency
3.1s
↓ 24.2% · 30d
3 runs ago
latest
overall WER · 35 models
Scribe v2
field · 34 models
lower-left is better
8 categories
WER
lower is better
Legal
2.8%
Technical
3.1%
General
5.4%
Medical
5.8%
Conversational
7.6%
Finance
7.6%
Code-Switching
14.6%
Noisy Environment
33.8%
5 accents
Rate
$0.004
/min
Per-second billing. Bring your own provider key and pay your provider directly — a 5% routing fee applies (first 100 min/mo free).
Set up BYOKCost estimator
1 hour
$0.24
10 hours
$2.41
100 hours
$24.12
1,000 hours
$241.20
Billed per second of audio processed.
Model ID
elevenlabs/scribe-v2
Authenticate every request with your secret API key as a Bearer token. Issue a key from your dashboard.
Use it with your agent
Paste this into Claude Code, Cursor, Codex or any agent with a shell. It installs the CLI and the OpenTranscription skill, then transcribes with this model.
Quickstart
Upload your audio, create a job with this model, then poll the job or set a webhook_url to be notified when it completes.
Key parameters
file_path
string
required
Storage path returned by the upload step.
model
string
required
The model to run this job on.
models
string[]
Ordered fallback chain: primary first, then backups tried in order if a provider fails.
language
string
ISO 639-1 language code. Omit to auto-detect.
diarization
boolean
Label speakers (A, B, …) in the output.
webhook_url
string
HTTPS URL notified with the result when the job completes. Delivered events are signed (X-OT-Signature).
title
string
Display name for this job in the dashboard. Falls back to the file name.
Response
A completed job returns the transcript in the OpenTranscription Unified Schema (OTUS).
Webhooks — skip polling
We POST a signed event to your webhook_url when a job completes or fails; verify the X-OT-Signature (HMAC-SHA256, reject if older than 300 s) and dedupe on the event id, then fetch the full transcript via GET /api/v1/transcriptions/{id}.
Rate-limited per tier — see the X-RateLimit-* response headers.
Full API referenceUptime · 30d
100.00%
Error rate
0.00%
Avg latency
65.9s
Last incident
None in 30d
from the same field
same benchmark, every match
Supported Languages
Supported Formats
Features
Limits
Max file size
3 GB
Max duration
10 h