View as Markdown
Rev.ai icon

Rev.ai ACTION

Submit Transcription Job

Starts an asynchronous job to transcribe speech-to-text for a media file. Add an optional callback URL to invoke when processing is complete.
  • Action
  • Writes data
  • Destructive
  • API key
  • SDK
  • MCP

IMPLEMENTATION

Call this tool

Connect a user's Rev.ai account once, then configure and run Submit Transcription Job from your backend or agent.

import { PipedreamClient } from "@pipedream/sdk"

const pd = new PipedreamClient({
  projectId: process.env.PIPEDREAM_PROJECT_ID!,
  clientId: process.env.PIPEDREAM_CLIENT_ID!,
  clientSecret: process.env.PIPEDREAM_CLIENT_SECRET!,
  projectEnvironment: "production",
})

const result = await pd.actions.run({
  id: "rev_ai-submit-transcription-job",
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  configuredProps: {
    rev_ai: { authProvisionId: "apn_xxxxxxx" },
    media_url: "Media url",
    skip_diarization: true,
  },
})

console.log(result)

SCHEMA

Inputs

Pipedream supplies the connected account. Your application provides the operation-specific values below. Dynamic inputs are resolved against that user's account.

Submit Transcription Job inputs
Property Type Description
media_url Media url string
Direct download media url. Ignored if submitting job from file
Required
skip_diarization Skip diarization boolean
Specify if speaker diarization will be skipped by the speech engine
Optional
skip_punctuation Skip punctuation boolean
Specify if "punct" type elements will be skipped by the speech engine. For JSON outputs, this includes removing spaces. For text outputs, words will still be delimited by a space
Optional
remove_disfluencies Remove disfluencies boolean
Currently we only define disfluencies as 'ums' and 'uhs'. When set to true, disfluencies will be not appear in the transcript.
Optional
filter_profanity Filter profanity boolean
Enabling this option will filter for approx. 600 profanities, which cover most use cases. If a transcribed word matches a word on this list, then all the characters of that word will be replaced by asterisks except for the first and last character.
Optional
speaker_channels_count Speaker channels count integer

Use to specify the total number of unique speaker channels in the audio.

Given the number of audio channels provided, each channel will be transcribed separately and the channel id assigned to the speaker label. The final output will be a combination of all individual channel outputs. Overlapping monologues will have ordering broken by the order in which the first spoken element of each monologue occurs. If speaker_channels_count is greater than the actual channels in the audio, the job will fail with invalid_media.

Note:

The amount charged will be the duration of the file multiplied by the number of channels specified. When using speaker_channels_count each channel will be diarized as one speaker, and the value of skip_diarization will be ignored if provided

Optional
delete_after_seconds Delete after seconds integer
Specify the number of seconds after job completion when job is auto-deleted. It may take up to 2 minutes after the scheduled time for the job to be deleted. The number of seconds provided must range from 0 seconds to 2592000 seconds (30 days).
Optional
metadata Metadata string
Optional metadata that was provided during submission
Optional
callback_url Callback url string
Optional callback url to invoke when processing is complete
Optional
phrases Phrases any

Array of phrases not found in normal dictionary. Add technical jargon, proper nouns and uncommon phrases as strings in this array to add them to the lexicon for this job.

A phrase must contain at least 1 alpha character but may contain any non-numeric character from the Basic Latin set. A phrase can contain up to 12 words. Each word can contain up to 34 characters.

Optional

REFERENCE

Tool details

Behavior hints are published with the component in the Pipedream registry and surface as MCP tool annotations, so an agent can reason about a tool before it calls it.

Registry key
rev_ai-submit-transcription-job
Version
0.1.3
App
Rev.ai
Authentication
API key
Read-only
No
Destructive
Yes
Open world
Yes