Audio & Video to Text Transcriber (Whisper) + SRT Subtitles
Pricing
from $7.00 / 1,000 audio minutes
Audio & Video to Text Transcriber (Whisper) + SRT Subtitles
Pricing
from $7.00 / 1,000 audio minutes
Rating
0.0
(0)
Developer
Miyuu Nishida
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
8 hours ago
Last modified
Security
Limited permissionsShare
Audio & Video Transcriber (Whisper) — Japanese & 90+ languages
Turn audio and video files into text with OpenAI Whisper. Paste direct links to your files and get the full transcript, timestamped segments and ready-to-use SRT subtitles. Works with Japanese and 90+ other languages, with automatic language detection.
No API key, no account elsewhere, no setup. Pay only per minute of audio.
Use cases
- Meeting, interview and lecture recordings → searchable text
- Podcasts and videos → subtitles (SRT) and show notes
- Japanese audio (日本語) → accurate Japanese text with proper punctuation spacing
- Bulk transcription of many files in one run
Input
| Field | Description |
|---|---|
audioUrls | Direct links to audio/video files: mp3, wav, m4a, mp4, webm, ogg, flac… up to 500 MB each. |
language | auto (default) or a language code such as ja, en, zh. Setting it improves accuracy. |
maxFiles | Safety limit on files per run (default 20). |
maxMinutesPerFile | Longer files are skipped and not charged (default 120). |
Page links such as YouTube watch pages are not supported. Use a direct file link (for example a public link from your cloud storage or podcast feed).
Output
One dataset item per file:
Each file's subtitles are also saved as SUBTITLES-1.srt, SUBTITLES-2.srt… in the key-value store.
Pricing
Pay per started minute of audio that is transcribed. Files that fail to download or exceed your limits are not charged. The Actor respects your maximum cost per run.
Notes
- Uses the Whisper small model on CPU with voice-activity detection to skip silence.
- Accuracy depends on audio quality, accents and background noise.
- Only transcribe recordings you have the right to use.
More tools from the same author
- SEO Audit & AI Search Readiness Checker: full-site SEO audit, AI search readiness score and llms.txt generator
- Bulk PageSpeed & Core Web Vitals Checker: Lighthouse scores, LCP/CLS/TBT and top fixes for a list of URLs
日本語
音声・動画ファイルのURLを入れるだけで、OpenAIのWhisperで文字起こしします。全文テキスト、タイムスタンプ付きの区切り、SRT字幕を出力します。日本語を含む90以上の言語に対応し、言語は自動判定もできます。APIキーは不要で、料金は音声1分ごとの従量課金です。
