ElevenLabs: Speech to text

Upload an audio or video file to transcribe its speech into accurate, editable text.

About

This ComfyUI workflow leverages the powerful capabilities of the ElevenLabs model to transcribe speech from audio or video files into text. The workflow begins with the 'LoadAudio' or 'RecordAudio' node, which allows users to either upload an existing audio file or record new audio directly within the interface.

Once the audio input is secured, the 'ElevenLabsSpeechToText' node processes the audio data, utilizing advanced speech recognition algorithms to convert spoken words into accurate text. This text is then made available for preview and editing through the 'PreviewAny' node, ensuring that users can review and refine the transcription as needed.

This workflow is particularly useful for creating transcripts from interviews, lectures, or any spoken content, making it an invaluable tool for content creators, researchers, and professionals who need to convert speech to text efficiently.

What you provide

Reading the workflow

Runs in ComfyUI. This workflow can't run on this page. Open it in Comfy Cloud with everything loaded, or download it for your own ComfyUI.

Try in Cloud

Output

Use this workflow from code

Generated from the workflow graph and inputs when possible; stored examples are shown otherwise. Review credentials and endpoints before running code, which may incur charges.

Get API key

What you need

Runs on: Comfy Cloud
Key: COMFY_API_KEY

Needs a paid Cloud plan and credits.

Download API JSON

# Python 3.10+: pip install comfy-sdk==0.4.0
import os

from comfy_sdk import Comfy

api_key = os.environ.get("COMFY_API_KEY", "").strip()
if not api_key: raise RuntimeError("Set COMFY_API_KEY")
os.environ.setdefault("COMFY_BASE_URL", "https://cloud.comfy.org")
client = Comfy(api_key=api_key)
workflow = client.workflows.from_json({
    "218": {
        "class_type": "ElevenLabsSpeechToText",
        "inputs": {
            "audio": [
                "219",
                0
            ],
            "language_code": "",
            "model": "scribe_v2",
            "model.diarization_threshold": 0.22,
            "model.diarize": False,
            "model.tag_audio_events": False,
            "model.temperature": 0,
            "model.timestamps_granularity": "word",
            "num_speakers": 0,
            "seed": 519926995
        },
        "_meta": {
            "title": "ElevenLabs Speech to Text"
        }
    },
    "219": {
        "class_type": "LoadAudio",
        "inputs": {
            "audio": "voice_demo.mp3"
        },
        "_meta": {
            "title": "Load Audio"
        }
    },
    "221": {
        "class_type": "PreviewAny",
        "inputs": {
            "source": [
                "218",
                0
            ]
        },
        "_meta": {
            "title": "Preview as Text"
        }
    },
    "222": {
        "class_type": "PreviewAny",
        "inputs": {
            "source": [
                "218",
                2
            ]
        },
        "_meta": {
            "title": "words_json"
        }
    }
})

# run() also passes api_key to the partner nodes in this workflow.
job = client.run(workflow, api_key=api_key)

API documentation

ElevenLabs: Speech to text

About

What you provide

Inside the workflow

Requires custom nodes

Use this workflow from code

What you need

Questions & answers

About

What you provide

Inside the workflow

Requires custom nodes

Use this workflow from code

What you need

Questions & answers

What formats are supported for audio input?

Can I edit the transcribed text within the workflow?

How accurate is the transcription from the ElevenLabs model?

Is it possible to transcribe multiple languages?