elevenlabs/scribe-v2

Name: Scribe V2
Author: ElevenLabs

Scribe V2 is ElevenLabs's speech recognition model. Transcribe audio content with industry-leading accuracy across multiple languages and accents.

Input

Audio Url(string)

URL of the audio file to transcribe

Tag Audio Events(boolean)

Tag audio events like laughter, applause, etc.

Diarize(boolean)

Whether to annotate who is speaking

Language Code(string)

Language code of the audio

Idle

Example output — click Run to generate your own

Production endpoint

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

POSThttps://api.sandbase.ai/v1/run

Model IDelevenlabs/scribe-v2

Input Schema

4 parameters · 0 required · 4 optional

Parameter	Type	Required	Description
`audio`	string	Optional	URL of the audio file to transcribe
`diarize`	boolean	Optional	Whether to annotate who is speaking · Default: true
`language_code`	string	Optional	Language code of the audio
`tag_audio_events`	boolean	Optional	Tag audio events like laughter, applause, etc. · Default: true

Output Schema

Field	Type	Description
`id`	string	Unique identifier for the generation task
`status`	string	Task status: pending, running, completed, failed, timeout
`model`	string	Model used for the generation
`outputs`	array	Array of output items
`outputs[].url`	string	URL of the generated artifact
`outputs[].content_type`	string	MIME type (e.g. image/png, video/mp4)
`error`	object \| null	Error details if failed, null on success
`error.type`	string	Machine-readable error type code
`error.message`	string	Human-readable error description

Async Workflow

This model uses asynchronous execution. Submit a request and poll for the result.

Submit — POST to /v1/run, receive an id
Poll — GET /v1/run/{id} until status is completed, failed, or timeout
Retrieve — Read outputs from the completed response

Code Examples

Ready-to-run snippets

# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "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,
  "prompt": "a beautiful sunset over mountains"
}'

# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
  -H "Authorization: Bearer YOUR_API_KEY"

← Back to Scribe V2

API README

Scribe V2

elevenlabs/scribe-v2 transcribes speech with language-aware recognition designed for accurate text from real-world audio, including recordings with several speakers and non-speech events. Scribe V2 can identify speaker turns and tag audible events, preserving useful context that a plain transcript would discard while also detecting or accepting the spoken language. This combination makes the model a practical choice when the creative outcome depends on those qualities rather than on a generic media conversion.

For production work, It fits interviews, meetings, podcasts, support calls, and media archives where searchable words, speaker attribution, and meaningful sounds all matter to the final record. The result is most reliable when the source material and creative brief clearly describe the intended subject, progression, visual or sonic character, and the qualities that must remain unchanged.

Highlights

High-accuracy speech recognition converts varied real-world recordings into readable text.

Speaker diarization separates and attributes turns in multi-person conversations.

Audio-event tagging records meaningful non-speech sounds alongside spoken content.

Multilingual transcription detects or follows the language used in the recording.

Pricing

Source audio length	Price
Per minute	$0.008

When to Use

✅ Good fit	❌ Consider alternatives
The model's named workflow matches the source material and intended output	A different input modality or model route is required
A managed asynchronous result is suitable for the production pipeline	A synchronous, interactive editor is essential
The documented controls cover the required duration, framing, or format	The project needs controls outside this endpoint's schema
Creative iteration benefits from a repeatable request structure	Exact deterministic pixels, frames, geometry, or samples are mandatory
A finished downloadable media asset is the desired deliverable	Editable source layers or a native project file are required

Prompt Guide

For audio transformation, state the intended result first, then add the subject or source treatment, progression, style, and delivery constraints. Keep one creative variable per phrase, use the documented field names for controls, and change one setting at a time when comparing results.

{
  "audio": "https://static.sandbase.ai/examples/elevenlabs/scribe-v2/input_audio_0.mp3"
}

Technical Specs

Spec	Value
Model ID	`elevenlabs/scribe-v2`
Inputs	audio, diarize, language_code, tag_audio_events
Required inputs	None
Output fields	language_code, text
Execution	Async (submit, then poll for result)