Use Scribe-V2 from ElevenLabs to do blazingly fast speech to text inferences!

fal-ai/elevenlabs/speech-to-text/scribe-v2

Use Scribe-V2 from ElevenLabs to do blazingly fast speech to text inferences!

Learn more about Speech to Text

Inference

Commercial use

Partner

Schema

LLMs

Playground API Examples

Input

Prompt*

Additional Settings

Customize your input with more control.

Result

Idle

What would you like to do next?

fal-ai/elevenlabs/speech-to-text/scribe-v2

Schema

Input

Prompt*

Additional Settings

Customize your input with more control.

Result

Idle

What would you like to do next?

ElevenLabs Scribe V2 (Speech to Text) API on fal

Input

Audio Url*

Hint: Drag and drop audio files from your computer, audio from web pages, paste from clipboard (Ctrl/Cmd+V), or provide a URL. Accepted file types: mp3, ogg, wav, m4a, aac

Keyterms

Additional Settings

Customize your input with more control.

Your request will cost $0.008 per input audio minutes. If keyterm is used, you request will cost %30 more.

Result

Idle

Hey, this is a test recording for Scribe version two, which is now available on fal.ai

What would you like to do next?

{
  "text": "Hey, this is a test recording for Scribe version two, which is now available on fal.ai",
  "words": [
    {
      "end": 0.539,
      "text": "Hey,",
      "type": "word",
      "start": 0.079,
      "speaker_id": "speaker_0"
    },
    {
      "end": 0.599,
      "text": " ",
      "type": "spacing",
      "start": 0.539,
      "speaker_id": "speaker_0"
    },
    {
      "end": 0.679,
      "text": "this",
      "type": "word",
      "start": 0.599,
      "speaker_id": "speaker_0"
    },
    {
      "end": 0.739,
      "text": " ",
      "type": "spacing",
      "start": 0.679,
      "speaker_id": "speaker_0"
    },
    {
      "end": 0.799,
      "text": "is",
      "type": "word",
      "start": 0.739,
      "speaker_id": "speaker_0"
    },
    {
      "end": 0.939,
      "text": " ",
      "type": "spacing",
      "start": 0.799,
      "speaker_id": "speaker_0"
    },
    {
      "end": 0.939,
      "text": "a",
      "type": "word",
      "start": 0.939,
      "speaker_id": "speaker_0"
    },
    {
      "end": 0.959,
      "text": " ",
      "type": "spacing",
      "start": 0.939,
      "speaker_id": "speaker_0"
    },
    {
      "end": 1.179,
      "text": "test",
      "type": "word",
      "start": 0.959,
      "speaker_id": "speaker_0"
    },
    {
      "end": 1.219,
      "text": " ",
      "type": "spacing",
      "start": 1.179,
      "speaker_id": "speaker_0"
    },
    {
      "end": 1.719,
      "text": "recording",
      "type": "word",
      "start": 1.22,
      "speaker_id": "speaker_0"
    },
    {
      "end": 1.719,
      "text": " ",
      "type": "spacing",
      "start": 1.719,
      "speaker_id": "speaker_0"
    },
    {
      "end": 1.86,
      "text": "for",
      "type": "word",
      "start": 1.719,
      "speaker_id": "speaker_0"
    },
    {
      "end": 1.879,
      "text": " ",
      "type": "spacing",
      "start": 1.86,
      "speaker_id": "speaker_0"
    },
    {
      "end": 2.24,
      "text": "Scribe",
      "type": "word",
      "start": 1.879,
      "speaker_id": "speaker_0"
    },
    {
      "end": 2.319,
      "text": " ",
      "type": "spacing",
      "start": 2.24,
      "speaker_id": "speaker_0"
    },
    {
      "end": 2.759,
      "text": "version",
      "type": "word",
      "start": 2.319,
      "speaker_id": "speaker_0"
    },
    {
      "end": 2.779,
      "text": " ",
      "type": "spacing",
      "start": 2.759,
      "speaker_id": "speaker_0"
    },
    {
      "end": 3.379,
      "text": "two,",
      "type": "word",
      "start": 2.779,
      "speaker_id": "speaker_0"
    },
    {
      "end": 3.399,
      "text": " ",
      "type": "spacing",
      "start": 3.379,
      "speaker_id": "speaker_0"
    },
    {
      "end": 3.519,
      "text": "which",
      "type": "word",
      "start": 3.399,
      "speaker_id": "speaker_0"
    },
    {
      "end": 3.539,
      "text": " ",
      "type": "spacing",
      "start": 3.519,
      "speaker_id": "speaker_0"
    },
    {
      "end": 3.659,
      "text": "is",
      "type": "word",
      "start": 3.539,
      "speaker_id": "speaker_0"
    },
    {
      "end": 3.699,
      "text": " ",
      "type": "spacing",
      "start": 3.659,
      "speaker_id": "speaker_0"
    },
    {
      "end": 3.839,
      "text": "now",
      "type": "word",
      "start": 3.699,
      "speaker_id": "speaker_0"
    },
    {
      "end": 3.839,
      "text": " ",
      "type": "spacing",
      "start": 3.839,
      "speaker_id": "speaker_0"
    },
    {
      "end": 4.319,
      "text": "available",
      "type": "word",
      "start": 3.839,
      "speaker_id": "speaker_0"
    },
    {
      "end": 4.339,
      "text": " ",
      "type": "spacing",
      "start": 4.319,
      "speaker_id": "speaker_0"
    },
    {
      "end": 4.579,
      "text": "on",
      "type": "word",
      "start": 4.339,
      "speaker_id": "speaker_0"
    },
    {
      "end": 4.599,
      "text": " ",
      "type": "spacing",
      "start": 4.579,
      "speaker_id": "speaker_0"
    },
    {
      "end": 5.699,
      "text": "fal.ai",
      "type": "word",
      "start": 4.599,
      "speaker_id": "speaker_0"
    }
  ],
  "language_code": "eng",
  "language_probability": 1
}

Your request will cost $0.008 per input audio minutes. If keyterm is used, you request will cost %30 more.

Input

Prompt*

Additional Settings

Customize your input with more control.

Result

Idle

What would you like to do next?

Input

Audio Url*

Hint: Drag and drop audio files from your computer, audio from web pages, paste from clipboard (Ctrl/Cmd+V), or provide a URL. Accepted file types: mp3, ogg, wav, m4a, aac

Keyterms

Additional Settings

Customize your input with more control.

Your request will cost $0.008 per input audio minutes. If keyterm is used, you request will cost %30 more.

Result

Idle

Hey, this is a test recording for Scribe version two, which is now available on fal.ai

What would you like to do next?

{
  "text": "Hey, this is a test recording for Scribe version two, which is now available on fal.ai",
  "words": [
    {
      "end": 0.539,
      "text": "Hey,",
      "type": "word",
      "start": 0.079,
      "speaker_id": "speaker_0"
    },
    {
      "end": 0.599,
      "text": " ",
      "type": "spacing",
      "start": 0.539,
      "speaker_id": "speaker_0"
    },
    {
      "end": 0.679,
      "text": "this",
      "type": "word",
      "start": 0.599,
      "speaker_id": "speaker_0"
    },
    {
      "end": 0.739,
      "text": " ",
      "type": "spacing",
      "start": 0.679,
      "speaker_id": "speaker_0"
    },
    {
      "end": 0.799,
      "text": "is",
      "type": "word",
      "start": 0.739,
      "speaker_id": "speaker_0"
    },
    {
      "end": 0.939,
      "text": " ",
      "type": "spacing",
      "start": 0.799,
      "speaker_id": "speaker_0"
    },
    {
      "end": 0.939,
      "text": "a",
      "type": "word",
      "start": 0.939,
      "speaker_id": "speaker_0"
    },
    {
      "end": 0.959,
      "text": " ",
      "type": "spacing",
      "start": 0.939,
      "speaker_id": "speaker_0"
    },
    {
      "end": 1.179,
      "text": "test",
      "type": "word",
      "start": 0.959,
      "speaker_id": "speaker_0"
    },
    {
      "end": 1.219,
      "text": " ",
      "type": "spacing",
      "start": 1.179,
      "speaker_id": "speaker_0"
    },
    {
      "end": 1.719,
      "text": "recording",
      "type": "word",
      "start": 1.22,
      "speaker_id": "speaker_0"
    },
    {
      "end": 1.719,
      "text": " ",
      "type": "spacing",
      "start": 1.719,
      "speaker_id": "speaker_0"
    },
    {
      "end": 1.86,
      "text": "for",
      "type": "word",
      "start": 1.719,
      "speaker_id": "speaker_0"
    },
    {
      "end": 1.879,
      "text": " ",
      "type": "spacing",
      "start": 1.86,
      "speaker_id": "speaker_0"
    },
    {
      "end": 2.24,
      "text": "Scribe",
      "type": "word",
      "start": 1.879,
      "speaker_id": "speaker_0"
    },
    {
      "end": 2.319,
      "text": " ",
      "type": "spacing",
      "start": 2.24,
      "speaker_id": "speaker_0"
    },
    {
      "end": 2.759,
      "text": "version",
      "type": "word",
      "start": 2.319,
      "speaker_id": "speaker_0"
    },
    {
      "end": 2.779,
      "text": " ",
      "type": "spacing",
      "start": 2.759,
      "speaker_id": "speaker_0"
    },
    {
      "end": 3.379,
      "text": "two,",
      "type": "word",
      "start": 2.779,
      "speaker_id": "speaker_0"
    },
    {
      "end": 3.399,
      "text": " ",
      "type": "spacing",
      "start": 3.379,
      "speaker_id": "speaker_0"
    },
    {
      "end": 3.519,
      "text": "which",
      "type": "word",
      "start": 3.399,
      "speaker_id": "speaker_0"
    },
    {
      "end": 3.539,
      "text": " ",
      "type": "spacing",
      "start": 3.519,
      "speaker_id": "speaker_0"
    },
    {
      "end": 3.659,
      "text": "is",
      "type": "word",
      "start": 3.539,
      "speaker_id": "speaker_0"
    },
    {
      "end": 3.699,
      "text": " ",
      "type": "spacing",
      "start": 3.659,
      "speaker_id": "speaker_0"
    },
    {
      "end": 3.839,
      "text": "now",
      "type": "word",
      "start": 3.699,
      "speaker_id": "speaker_0"
    },
    {
      "end": 3.839,
      "text": " ",
      "type": "spacing",
      "start": 3.839,
      "speaker_id": "speaker_0"
    },
    {
      "end": 4.319,
      "text": "available",
      "type": "word",
      "start": 3.839,
      "speaker_id": "speaker_0"
    },
    {
      "end": 4.339,
      "text": " ",
      "type": "spacing",
      "start": 4.319,
      "speaker_id": "speaker_0"
    },
    {
      "end": 4.579,
      "text": "on",
      "type": "word",
      "start": 4.339,
      "speaker_id": "speaker_0"
    },
    {
      "end": 4.599,
      "text": " ",
      "type": "spacing",
      "start": 4.579,
      "speaker_id": "speaker_0"
    },
    {
      "end": 5.699,
      "text": "fal.ai",
      "type": "word",
      "start": 4.599,
      "speaker_id": "speaker_0"
    }
  ],
  "language_code": "eng",
  "language_probability": 1
}

Your request will cost $0.008 per input audio minutes. If keyterm is used, you request will cost %30 more.