ElevenLabs Scribe review

Scribe is the speech-to-text side of ElevenLabs, sold through the same API that runs its voices. Scribe v2 handles files in 90+ languages with keyterm prompting and dynamic audio tagging at $0.22 per hour, and Scribe v2 Realtime streams live audio with a published latency under 150 ms for $0.39 per hour. Keyterm prompting adds $0.05 per hour on batch and $0.08 on realtime, and transcript editing adds $0.07 or $0.12. A medical variant is HIPAA-eligible, with BAAs and a zero retention mode, and ElevenLabs says Scribe also supports on-premise configurations for enterprises. API usage is billed in US dollars per audio minute rather than in credits, which makes cost easy to forecast, and a free plan with monthly credits covers early tests. It also plugs directly into ElevenLabs Agents if you are building a voice agent there. The main drawback is price: realtime costs more than double AssemblyAI's streaming rate.

Who it is for

Voice agent and captioning teams that need many languages and a published latency under 150 ms.

Price

API pay as you go: Scribe v2 $0.22 per hour (about $0.0037 per minute), Scribe v2 Realtime $0.39 per hour; keyterm prompting $0.05 per hour extra.

speech to text $0.22 per hour (Scribe) or $0.39 per hour (Scribe Realtime)
Quoted from the vendor pricing page on November 7, 2026.

Key features

• Scribe v2 in 90+ languages with keyterm prompting and dynamic audio tagging
• Scribe v2 Realtime with sub-150 ms latency and word-level timestamps
• Built into ElevenLabs Agents for real-time voice agents
• Scribe v2 Medical, HIPAA-eligible with BAAs and zero retention mode
• Cloud and on-premise configurations for enterprises

Strengths and weaknesses

• Strength: Published sub-150 ms latency on the realtime model
• Strength: 90+ languages on both batch and realtime
• Strength: Free plan with monthly credits to try the models
• Weakness: Realtime costs $0.39 per hour, more than AssemblyAI or Speechmatics
• Weakness: Keyterm prompting and transcript editing are billed per hour on top
• Weakness: On-premise is for enterprises only

Key facts

• Languages: 90+
• Realtime latency: Under 150 ms
• Billing: API billed in US dollars per audio minute

Where it ranks

ElevenLabs Scribe is No. 4 in our Best Speech-to-Text APIs verdict.