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

# Speech-to-text models

> Every speech-to-text model on Infery, grouped by what it takes as input.

Transcription, through `POST /v1/audio/transcriptions`.

**18 models.** Grouped by input, because that is the choice you make first — a model that
turns an image into a video is not interchangeable with one that starts from a prompt.

Prices are not listed here: they change, and a stale price is worse than none. See the
[live catalogue](https://infery.ai/models) for current rates, and each model's own page there for its full
parameter schema.

## Audio → text (18)

| Model                                 | Owner             | Also accepts | Notes                                                                                                                                     |
| ------------------------------------- | ----------------- | ------------ | ----------------------------------------------------------------------------------------------------------------------------------------- |
| `paraformer-v2`                       | alibaba           | —            |                                                                                                                                           |
| `qwen3-asr-flash`                     | alibaba           | —            |                                                                                                                                           |
| `cohere-transcribe`                   | cohere-transcribe | —            | Cohere Transcribe turns your business audio into accurate text, ready for search, analytics, and automation                               |
| `elevenlabs-speech-to-text`           | elevenlabs        | —            | Generate text from speech using ElevenLabs advanced speech-to-text model.                                                                 |
| `elevenlabs-speech-to-text-scribe-v2` | elevenlabs        | —            | Use Scribe-V2 from ElevenLabs to do blazingly fast speech to text inferences!                                                             |
| `gemini-2.5-flash-stt`                | google            | —            | 1049k ctx, 66k out                                                                                                                        |
| `smart-turn`                          | infery            | —            | An open source, community-driven and native audio turn detection model by Pipecat AI.                                                     |
| `speech-to-text`                      | infery            | —            | Leverage the rapid processing capabilities of AI models to enable accurate and efficient real-time speech-to-text transcription.          |
| `speech-to-text-stream`               | infery            | —            | Leverage the rapid processing capabilities of AI models to enable accurate and efficient real-time speech-to-text transcription.          |
| `speech-to-text-turbo`                | infery            | —            | Leverage the rapid processing capabilities of AI models to enable accurate and efficient real-time speech-to-text transcription.          |
| `speech-to-text-turbo-stream`         | infery            | —            | Leverage the rapid processing capabilities of AI models to enable accurate and efficient real-time speech-to-text transcription.          |
| `nemotron-3-nano-omni-audio`          | nvidia            | —            | Audio reasoning variant of NVIDIA's Nemotron 3 Nano Omni.                                                                                 |
| `nemotron-asr-multilingual-asr`       | nvidia            | —            | Nemotron-ASR-Streaming is a multi lingual, streaming Automatic Speech Recognition (ASR) engineered to deliver high-quality multi lingual… |
| `gpt-4o-mini-transcribe`              | openai            | —            | Speech-to-text model powered by GPT-4o mini                                                                                               |
| `gpt-4o-transcribe`                   | openai            | —            | Speech-to-text model powered by GPT-4o                                                                                                    |
| `gpt-4o-transcribe-diarize`           | openai            | —            |                                                                                                                                           |
| `whisper-1`                           | openai            | —            |                                                                                                                                           |
| `silero-vad`                          | silero-vad        | —            | Detect speech presence and timestamps with accuracy and speed using the ultra-lightweight Silero VAD model                                |