Scribe V2
elevenlabs/scribe-v2Scribe V2 is ElevenLabs's speech recognition model. Transcribe audio content with industry-leading accuracy across multiple languages and accents.
- Base price
- $0.008USD / run
- Execution
- async
- Model type
- audio
- Input fields
- 4
Try the model
Playground
Your output will appear here
Complete the inputs, then click Run.
Model card
Specifications
Pricing
- Base price
- $0.008 / run
Context & modalities
- Input
- Schema-defined
- Output
- audio
Capabilities
- Chat
- Not supported
- Vision
- Not supported
- Reasoning
- Not supported
- Structured output
- Not supported
- Function calling
- Not supported
- Audio input
- Not supported
Access
- Provider
- ElevenLabs
- Model ID
- elevenlabs/scribe-v2
- Execution
- async
- Base URL
- https://api.sandbase.ai
- API
- Unified Run API
- Endpoint
- /v1/run
API README
Scribe V2
ElevenLabs Scribe v2 transcribes speech in 90+ languages with speaker diarization and tags for non-speech audio events.
Fields
| Field | Type | Default | Notes |
|---|---|---|---|
audio | audio URL | — | Audio or video URL. |
tag_audio_events | boolean | true | Mark laughter, music, and other events. |
diarize | boolean | true | Label who is speaking. |
language_code | string | — | Force a language; omit to detect. |
Billing
$0.008 per started minute of audio. The quote before submission assumes 1 minute; the final charge uses the measured length.
| Audio | Price |
|---|---|
| 1 min | $0.008 |
| 10 min | $0.08 |
| 60 min | $0.48 |
Failed runs are not charged.
Start building
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "elevenlabs/scribe-v2",
"audio": "https://static.sandbase.ai/examples/elevenlabs/scribe-v2/input_audio_0.mp3",
"diarize": true,
"language_code": "eng",
"tag_audio_events": true
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
status=$(printf '%s' "$result" | jq -r .status)
case "$status" in completed|failed|timeout) break ;; esac
sleep 2
result=$(curl --fail-with-body --silent \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
"https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"Choose your model
Compare models
| Model | Type | Default price | Released |
|---|---|---|---|
Scribe V2This model ElevenLabs | Audio | $0.01 / run | Jan 14, 2026 |
ElevenLabs | Audio | $0.04 / run | Sep 28, 2026 |
ElevenLabs | Audio | $0.08 / run | Sep 28, 2026 |
ElevenLabs | Audio | $0.75 / run | Sep 14, 2026 |
ElevenLabs | Audio | $0.75 / run | Sep 14, 2026 |
ElevenLabs | Audio | $0.60 / run | Dec 22, 2025 |
Questions
FAQ
How do I call ElevenLabs Scribe V2 through SandBase?
Create a SandBase API key, then send requests with the model ID "elevenlabs/scribe-v2" to Unified Run API (/v1/run) at https://api.sandbase.ai. The request examples on this page show the exact payload.
Do I need a separate ElevenLabs account?
No. One SandBase API key and balance gives you access to ElevenLabs Scribe V2 and the other models in the catalog; you do not need to sign up with ElevenLabs separately.
