Tiktok Video Transcirpt Using OpenAI Whisper API avatar
Tiktok Video Transcirpt Using OpenAI Whisper API

Pricing

$2.00/month + usage

Go to Store
Tiktok Video Transcirpt Using OpenAI Whisper API

Tiktok Video Transcirpt Using OpenAI Whisper API

Developed by

ius iyb

ius iyb

Maintained by Community

This Apify actor uses the OpenAI Whisper API to either transcribe Tiktok video into its original language or translate it into English. It's built to be robust, automatically handling video-to-audio conversion and compression to stay within API limits.

0.0 (0)

Pricing

$2.00/month + usage

0

Total users

1

Monthly users

1

Last modified

4 days ago

TikTok Video URL

tiktokUrlstringRequired

The URL of the TikTok video you want to process.

OpenAI API Key

openaiApiKeystringRequired

Your OpenAI API key. Best practice is to set this as a secret environment variable.

Task Type

taskEnumOptional

Choose whether to transcribe the audio into its original language or translate it into English.

Value options:

"transcription": string"translation": string

Transcription Model

modelEnumOptional

Select the model. Note: 'translation' and 'timestamp_granularities' tasks require 'whisper-1'.

Value options:

"whisper-1": string"gpt-4o-transcribe": string"gpt-4o-mini-transcribe": string

Language (Optional)

languagestringOptional

The language of the audio in ISO-639-1 format (e.g., 'en', 'es'). Improves accuracy. Required by some models.

Prompt (Optional)

promptstringOptional

A prompt to guide the model's style or to correct specific words and acronyms.

Response Format

response_formatEnumOptional

The output format. Note: 'gpt-4o-*' models only support 'json' or 'text'. Timestamps require 'verbose_json'.

Value options:

"json": string"text": string"srt": string"verbose_json": string"vtt": string

Temperature (Optional)

temperaturestringOptional

A value between 0 and 1. Higher values (e.g., 0.8) are more random; lower values (e.g., 0.2) are more focused.

Timestamp Granularities (Optional)

timestamp_granularitiesarrayOptional

Request word or segment-level timestamps. Requires 'whisper-1' model and 'verbose_json' response format.