Spark
Sign In
Prompt Chain

Generate Subtitles from Audio and Transcripts

Prompt workflow that generates time-aligned subtitles in SRT or VTT format from audio files and transcripts using ElevenLabs forced alignment API.

Copy chain
Works with elevenlabs
Promptfoo
Maintainer?
54
Spark score
out of 100
Updated 2 days ago
Version code-scan-action-0.1
Add to Favorites

Why it matters

Automate the creation of time-aligned subtitles (SRT/VTT) for audio and transcript content. This asset leverages ElevenLabs' forced alignment capabilities to accurately synchronize spoken words with timestamps.

Outcomes

What it gets done

01

Process audio files to extract speech.

02

Utilize ElevenLabs for accurate speech-to-text alignment.

03

Generate SRT and VTT subtitle files based on aligned data.

04

Ensure precise timing for subtitles matching the audio.

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/pfoo-elevenlabs-alignment | bash

Capabilities

What this chain does

Transcribe

Converts audio or video speech to written text.

Extract

Pulls structured data fields from unstructured text.

Overview

Elevenlabs Alignment

What it does

This prompt chain automates subtitle generation by processing audio files and transcripts through the ElevenLabs forced alignment API. It outputs time-aligned subtitle files in SRT or VTT format, with each line of text synchronized to the corresponding audio segment. The workflow handles the technical alignment process that matches transcript words to precise audio timestamps.

How it connects

Use this when you need to add subtitles or captions to video or audio content and already have a transcript. It's ideal for content creators, video editors, and accessibility teams who want to automate the time-consuming process of manually timing subtitle cues to match spoken audio.

Source README

yaml-language-server: $schema=../../site/static/config-schema.json

description: ElevenLabs Forced Alignment - Subtitle generation

Alignment uses audio files + transcripts - pass via vars

prompts:

  • '{{transcript}}'

providers:

Basic alignment (JSON output)

  • id: elevenlabs:alignment:json
    label: Alignment (JSON)

SRT subtitle format

  • id: elevenlabs:alignment:srt
    label: Alignment (SRT Subtitles)

Default test configuration

defaultTest:

All tests will require alignment to complete

assert:
- type: not-contains
value: error

tests:

  • description: Align Armstrong moon landing speech
    vars:
    audioFile: examples/elevenlabs-stt/audio/sample1.mp3
    transcript: "That's one small step for man, one giant leap for mankind."
    format: json
    assert:

    • type: javascript
      value: output.includes('words')
    • type: not-contains
      value: error

  • description: Align Armstrong to SRT format
    vars:
    audioFile: examples/elevenlabs-stt/audio/sample1.mp3
    transcript: "That's one small step for man, one giant leap for mankind."
    format: srt
    assert:

    • type: javascript
      value: output.includes('-->') && output.includes('small step')

  • description: Align sample2 hello message
    vars:
    audioFile: examples/elevenlabs-stt/audio/sample2.wav
    transcript: "Hello. What's today's date? Could you please let me know?"
    format: json
    assert:

    • type: javascript
      value: output.includes('words')
    • type: not-contains
      value: error

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.