Transcription

From 0.8 credits

Transcribe any video or audio file to text. Timestamps, speaker detection, and 99+ language support.

Video or Audio File

Click to upload video

or drag and drop

Browse library

Language

Speaker Detection

Label who is speaking. Turn on for interviews and multi-speaker recordings.

Number of Speakers (0 = auto)

0 – 20

Word Corrections

Optional word-boundary substitutions applied to the rendered SRT and TXT, useful when the recognizer mis-hears a specific word (a name, an acronym, a domain term) and writes it the same wrong way every time. Each key is the word as transcribed; the value is the correct spelling. Case-sensitive; matches must align to whole words. Leave empty to ship the transcript exactly as the recognizer wrote it.

Still needed: Video or Audio File

Runs on

1 models

ElevenLabs
- ElevenLabs Scribe v2

Transcription API

Call this pipeline from your own code. One request dispatches a run; the model is an input field, not a separate endpoint.

Get an API token

inputs: 5
required: 1
Pricing: from 0.8 credits

Language

TypeScript Python Go CLI

bun add @pipe2-ai/sdk

Run a pipeline

import { createClient } from "@pipe2-ai/sdk";

const client = createClient(process.env.PIPE2_TOKEN!);

const { run_pipeline } = await client.RunPipeline({
  pipeline_slug: "transcription",
  input: {
    source_asset_id: "a1b2c3d4-0000-4000-8000-000000000001",
  },
});

pip install pipe2

Run a pipeline

import asyncio
import os

from pipe2 import Pipe2Client

client = Pipe2Client(token=os.environ["PIPE2_TOKEN"])

run = asyncio.run(client.run_pipeline(
    pipeline_slug="transcription",
    input={
        "source_asset_id": "a1b2c3d4-0000-4000-8000-000000000001",
    },
))

go get github.com/pipe2-ai/sdk-go

Run a pipeline

client := pipe2.NewClient(os.Getenv("PIPE2_TOKEN"))

input := json.RawMessage(`{
  "source_asset_id": "a1b2c3d4-0000-4000-8000-000000000001"
}`)

run, err := pipe2.RunPipeline(context.Background(), client, "transcription", input)
if err != nil {
    log.Fatal(err)
}

brew install pipe2-ai/tap/pipe2

Run a pipeline

pipe2 pipelines run \
  --pipeline transcription \
  --input-json '{"source_asset_id": "a1b2c3d4-0000-4000-8000-000000000001"}' \
  --wait

Per page

Input	Type	default	Description
`source_asset_id`required	string	default—	Audio or video to transcribe. Asset id returned by an upload. See /docs/api/ for the upload flow.
`corrections`	object	default{}	Optional word-boundary substitutions applied to the rendered SRT and TXT, useful when the recognizer mis-hears a specific word (a name, an acronym, a domain term) and writes it the same wrong way every time. Each key is the word as transcribed; the value is the correct spelling. Case-sensitive; matches must align to whole words. Leave empty to ship the transcript exactly as the recognizer wrote it.
`diarize`	boolean	defaultfalse	Label who is speaking. Turn on for interviews and multi-speaker recordings.
`language_code`	enum	defaultauto	Spoken language. Leave unset to detect it from the audio. auto · en · es +8 `autoenesptfrdehiarjakozh`
`num_speakers`	integer	default0	How many speakers to expect. Leave unset to detect automatically.

Point any MCP client at pipe2 and your agent gets these tools. It finds this pipeline, reads the same schema above, then runs it.

list_pipelines
get_pipeline_schema
run_pipeline
get_pipeline_run_status
request_upload

https://mcp.pipe2.ai/mcp

{
  "mcpServers": {
    "pipe2ai": {
      "url": "https://mcp.pipe2.ai/mcp",
      "headers": { "Authorization": "Bearer YOUR_TOKEN" }
    }
  }
}

MCP setup

Full API reference CLI reference

Recipes using this pipeline

Show all recipes

Articles about this pipeline

Show all articles

Frequently Asked Questions

What file formats are supported?

Any video or audio file, MP4, MOV, AVI, MP3, WAV, M4A, FLAC, and more. The pipeline automatically extracts the audio track from video files.

How accurate is the transcription?

Word-error rates under 5% for clear audio in major languages. Accuracy depends on audio quality, background noise, and speaker clarity.

What is speaker detection?

When enabled, the transcript labels each segment with the speaker who said it ([speaker_0], [speaker_1], etc.). Use the Number of Speakers hint to improve accuracy when you know how many people are in the recording.

Which languages are supported?

99 languages with automatic detection. Set a specific language for best accuracy when you know the source language.

How long does it take?

Typically 10-30% of the audio duration. A 10-minute recording takes 1-3 minutes to transcribe.