> ## 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.

# Migration Guides

> The differences between Ink and other models

Ink supports two realtime transcription modes:

1. Client sends audio (**Auto** finalization)
2. Client sends audio and signals when to finalize transcripts (**Manual** finalization)

Most speech-to-text APIs combine both behaviors, but Cartesia separates them for improved model performance.

**Auto finalization is recommended** for most agents.

At the same time, there are many use-cases where manual finalization is necessary. Some examples are:

1. Push-to-talk apps
2. Pipelines where you know speech is over and are waiting for the transcript

## Guides

* [**Deepgram Turn-based Audio (Flux)**](/use-the-api/stt/migrate-from-deepgram-flux)
* **Deepgram Live Audio (Nova)**
  * [Auto finalization](/use-the-api/stt/migrate-from-deepgram-nova/auto)\
    Ink automatically finalizes transcripts
  * [Manual finalization](/use-the-api/stt/migrate-from-deepgram-nova/manual)\
    Your client decides when to finalize transcripts
* **ElevenLabs Realtime Speech to Text**
  * [Auto finalization](/use-the-api/stt/migrate-from-elevenlabs-realtime-speech-to-text/auto)\
    Similar to ElevenLabs's `commit_strategy=vad`
  * [Manual finalization](/use-the-api/stt/migrate-from-elevenlabs-realtime-speech-to-text/manual)\
    Similar to ElevenLabs's `commit_strategy=manual`
* **OpenAI Realtime Transcription**
  * [Auto finalization](/use-the-api/stt/migrate-from-openai-realtime-transcription/auto)\
    Similar to OpenAI's `turn_detection: server_vad`
  * [Manual finalization](/use-the-api/stt/migrate-from-openai-realtime-transcription/manual)\
    Similar to OpenAI's `turn_detection: null`
* [**OpenAI Speech to Text**](/use-the-api/stt/migrate-from-openai-speech-to-text)\
  Batch audio transcription