> ## Documentation Index
> Fetch the complete documentation index at: https://docs.cartesia.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Pricing

> How Cartesia charges for usage

Cartesia meters model usage in **credits** and agent usage in **agent dollars**.

Every subscription plan includes a monthly credit allotment. See [cartesia.ai/pricing](https://cartesia.ai/pricing) for current plans and included credits.

Credits are only used by successful requests; errors will not consume credits.

## At a glance

| Capability          | Endpoint                                                                                                                                                | Cost                                           |
| ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------- |
| Agents              | [Line](/line/introduction)                                                                                                                              | Billed per minute in USD, not credits          |
| TTS                 | [`/tts/bytes`](/api-reference/tts/bytes), [`/tts/sse`](/api-reference/tts/sse), [`/tts/websocket`](/api-reference/tts/websocket)                        | \~1 credit per character                       |
| PVC / Fine-tune TTS | [`/tts/bytes`](/api-reference/tts/bytes), [`/tts/sse`](/api-reference/tts/sse), [`/tts/websocket`](/api-reference/tts/websocket)                        | \~1.5 credits per character                    |
| STT                 | [`/stt`](/api-reference/stt/transcribe), [`/stt/websocket`](/api-reference/stt/websocket), [`/stt/turns/websocket`](/api-reference/stt/turns/websocket) | Depends on endpoint, model, and audio duration |
| PVC Fine-Tuning     | [`/fine-tunes/create`](/api-reference/fine-tunes/create)                                                                                                | 1 million credits per fine-tune                |
| Infill              | [`/infill/bytes`](/api-reference/infill/bytes)                                                                                                          | 300 credits + \~1 credit per character         |
| Voice changer       | [`/voice-changer/bytes`](/api-reference/voice-changer/bytes), [`/voice-changer/sse`](/api-reference/voice-changer/sse)                                  | 15 credits per second                          |

## Agents

Cartesia's hosted [Line](/line/integrations/overview) voice agents are billed per minute in US dollars. This does not affect your credit balance.

| Feature            | Price per minute | Notes                                            |
| ------------------ | ---------------- | ------------------------------------------------ |
| Agent calling      | \$0.06           | Base rate for all voice agent calls              |
| Telephony (add-on) | +\$0.014         | Additional when using a Cartesia-provided number |

## Text-to-speech

Standard TTS costs approximately 1 credit per character. The exact number of credits can vary slightly due to transcript pre-processing.

This applies to every TTS endpoint: [`/tts/bytes`](/api-reference/tts/bytes), [`/tts/sse`](/api-reference/tts/sse), and [`/tts/websocket`](/api-reference/tts/websocket).

### TTS with a Pro Voice Clone

Generating speech with a [Pro Voice Clone](/build-with-cartesia/capability-guides/clone-voices-pro) costs approximately 1.5 credits per character, 50% more than standard TTS, because it runs on a bespoke model fine-tuned to your data.

This does not apply to [Instant Voice Clones](/build-with-cartesia/capability-guides/clone-voices), which are billed at the standard rate.

## Speech-to-text

STT pricing depends on the model and whether you use the batch or realtime endpoint. Silence is also included, even if no transcript is produced.

| Endpoint                                                     | `ink-2`                       | `ink-whisper`                   |
| ------------------------------------------------------------ | ----------------------------- | ------------------------------- |
| [`/stt/websocket`](/api-reference/stt/websocket)             | 3 credits per second of audio | 1 credit per second of audio    |
| [`/stt/turns/websocket`](/api-reference/stt/turns/websocket) | 3 credits per second of audio | 1 credit per second of audio    |
| [`/stt`](/api-reference/stt/transcribe)                      | Not available yet             | 1 credit per 2 seconds of audio |

## Pro Voice Clone Fine-Tuning

Creating a [Pro Voice Clone](/build-with-cartesia/capability-guides/clone-voices-pro) fine-tunes a model on your data via [`/fine-tunes/create`](/api-reference/fine-tunes/create) and costs 1,000,000 credits.

You're only charged when training succeeds. Pro Voice Clones are pinned to the base model they were trained on, so retraining on a new base model or new data costs another 1,000,000 credits.

## Infill

[Infill](/api-reference/infill/bytes) generates audio that bridges two existing clips. Each request costs a fixed 300 credits, plus the [standard TTS rate](#text-to-speech) applied to the infill transcript.

## Voice changer

Voice changer converts input audio into a target voice. It costs 15 credits per second of input audio on both [`/voice-changer/bytes`](/api-reference/voice-changer/bytes) and [`/voice-changer/sse`](/api-reference/voice-changer/sse).

## Check your usage

You can check your usage on the [usage page](https://play.cartesia.ai/usage) and view your current balance on the [subscription page](https://play.cartesia.ai/subscription).

Additionally, you can use the [credit usage](/api-reference/usage/credits) and [agent usage](/api-reference/usage/agents) API to check usage programmatically. This requires creating an [admin API key](/use-the-api/api-conventions#use-admin-api-keys-for-management-endpoints).