Skip to content

Scribe v2

Transcription across 99 languages with speaker diarization and word-level timestamps, billed at $0.22 per audio hour. Worth knowing that ElevenLabs credits are shared across its products, so heavy text-to-speech use can eat into the same allowance your transcription draws from.

Pricing checked against provider documentation on . How we verify

stable ElevenLabs Scribe scribe-v2

Price

$0.0037

/ audio min

Context

not token-based

Max output

varies

Pricing caveat: Published as $0.22 per audio hour. Entity detection adds $0.07/hour and keyterm prompting $0.05/hour. A realtime variant runs $0.39/hour (~$0.0065/min) at roughly 150 ms latency.

Where Scribe v2 fits

  • Multilingual transcription with speakers
  • Subtitling with word timings
  • Interview and research archives
  • Pipelines already using ElevenLabs voices

Specifications

API model ID
scribe-v2
Provider
ElevenLabs
Model family
Scribe
Released
March 2026
Knowledge cutoff
Context window
Max output
Native reasoning
No
Relative latency
medium
Input modalities
audio
Output modalities
text
Open weights
No
Cached input
Batch discount

Frequently asked

How much does Scribe v2 cost?

Scribe v2 is billed at $0.0037 / audio min.

What is Scribe v2's context window?

Context limits for Scribe v2 depend on the input format rather than a token count.

Is Scribe v2 a reasoning model?

No. Scribe v2 answers directly without a native thinking phase, which keeps latency and cost predictable.

What is Scribe v2 best for?

Widest language coverage with diarization. Transcription across 99 languages with speaker diarization and word-level timestamps, billed at $0.22 per audio hour. Worth knowing that ElevenLabs credits are shared across its products, so heavy text-to-speech use can eat into the same allowance your transcription draws from.