# elevenlabs API Models, Pricing and Capabilities Canonical HTML page: [elevenlabs API Models, Pricing and Capabilities]() Markdown alternative: [elevenlabs API Models, Pricing and Capabilities as Markdown]() Access 2 models from elevenlabs through the Impossibl API, including Scribe v2 and Scribe v2 Medical. Compare pricing per million tokens, context windows, and capabilities between different elevenlabs models. Select two or three models to [compare specifications and API costs](). Model types and billing units are not interchangeable. ## At a glance - models: 2 - modalities: takes audio in, gives text out - model types: speech to text ## Models ### [Scribe v2]() Scribe v2 is ElevenLabs' speech recognition model for transcribing recorded audio and video. It returns word-level timestamps, tags audio events such as laughter, and can label which speaker is talking across more than ninety languages. The advertised input rate is $0.00366667 per minute of audio. - API identifier: `elevenlabs/scribe-v2` - Creator: elevenlabs; model type: Speech to text. - Context window: Not published; tool calling: Not published. - Inputs: audio; outputs: text. - Base API pricing (USD): $0.00366667 per minute of audio. - [Complete model facts, cache rates, context tiers, and FAQs as Markdown]() ### [Scribe v2 Medical]() Scribe v2 Medical is ElevenLabs' speech recognition model tuned for clinical audio. It keeps the Scribe v2 API and languages while cutting errors on medical terminology, and is offered for HIPAA-eligible workloads. The advertised input rate is $0.00366667 per minute of audio. - API identifier: `elevenlabs/scribe-v2-medical` - Creator: elevenlabs; model type: Speech to text. - Context window: Not published; tool calling: Not published. - Inputs: audio; outputs: text. - Base API pricing (USD): $0.00366667 per minute of audio. - [Complete model facts, cache rates, context tiers, and FAQs as Markdown]() ## Compare elevenlabs models - [Scribe v2 vs Scribe v2 Medical](); [Markdown comparison]() ## Frequently asked questions ### Which elevenlabs models are available through Impossibl? The directory lists 2 models from elevenlabs available through the Impossibl API, including Scribe v2 and Scribe v2 Medical. Open each model page for its API identifier, capabilities, and current pricing. ### How much do elevenlabs models cost? elevenlabs model prices vary by model and usage. All rates below are published base API rates in USD. For audio-duration models, published input rates start at $0.00366667 per minute of audio. Individual model pages include published cache prices and billing units. Applicable fees and workspace-specific pricing can affect the amount paid. ### Does Impossibl add a markup to elevenlabs pricing? No. Usage is charged at the provider's list price with 0% usage markup. Prepaid credit purchases include a 5% platform fee, and there is no subscription. The rates on this page are elevenlabs's published base rates, and usage comes off your balance when the request finishes. ### What inputs and capabilities do elevenlabs models support? Available model types include speech to text. Published input support includes audio; support varies by model. Tool-calling support is unspecified for 2 models. ### How do I use elevenlabs models through an API? Use the exact model identifier from the model page with the Impossibl API. For example, select elevenlabs/scribe-v2 with /v1/audio/transcriptions. Endpoint compatibility depends on the selected model. The API quickstart explains how to create an API key and send a request. ## Sources and related links Prices, capabilities, limits, and availability describe the public Impossibl API offering. An unpublished fact is unknown; a published zero price is zero. Compare matching billing units and check context tiers before estimating costs. - [Public Impossibl model catalog]() - [Full model directory as JSON]() - [Model directory as Markdown]() - [API quickstart]() - [Model documentation]()