Last refreshed 2026-06-29. Next refresh: weekly.
Why use Scribe v1 on ElevenLabs API?
ElevenLabs API offers Scribe v1 with competitive pricing. ElevenLabs' API provides hosted text-to-speech, speech-to-speech, dubbing, and voice models for creative production and realtime conversational applications.
Input / 1M
-
Output / 1M
-
Cache
Not sourced
Batch
Not sourced
Setup recipe
Docs fallbackInstall
Use the provider REST API or SDKAuth
Create a provider API keyCall
model: scribe_v1Model ID
scribe_v1Request example
Curated snippets for this provider are not sourced yet. Use ElevenLabs API documentation with model ID
scribe_v1.Gotchas
- Use provider model ID "scribe_v1", not the LLMReference slug "scribe-v1".
Capabilities
Audio
About Scribe v1
Scribe v1 is ElevenLabs' first speech-to-text model, released February 26, 2025. Claimed world-leading accuracy at launch across 99 languages, with word-level timestamps, speaker diarization, and audio-event tagging. Now deprecated — users should migrate to scribe_v2. Pricing was $0.22/hr of audio. API ID: scribe_v1.
Get Started
Model Specs
Released2025-02-26
ArchitectureAudio / Speech