Speech to Text
Transcribe audio or a recording to text and subtitles (SRT, VTT) with Whisper.
Frequently Asked Questions
How do I transcribe an audio file?
Drop an audio file on the upload area or record from your microphone, pick the spoken language (or leave it on automatic), and click Transcribe. You get the text plus SRT and VTT subtitles you can copy or download.
Which file formats and sizes are supported?
MP3, WAV, M4A, OGG, WEBM, and FLAC files up to 25 MB. For a longer recording, compress it to a lower-bitrate MP3 or split it into parts.
Which languages does it support?
Whisper large-v3-turbo recognizes about 100 languages and detects the language automatically. Choosing the language yourself can improve accuracy on short or noisy clips. Choose Translate to English to get an English transcript of speech in any supported language.
How do I make subtitles for a video?
Upload the video file (WEBM or MP4 up to 25 MB) or its extracted audio, transcribe it, then open the SRT or VTT tab and download the file. Most video players and editors, including YouTube, accept both formats.
Is my audio stored?
Audio is sent to the ToolDock API and transcribed by Cloudflare Workers AI through Cloudflare AI Gateway, which keeps request logs and caches responses for up to 7 days. ToolDock does not store your audio or transcript in its own database.
Can I use this from code?
Yes. POST /api/v1/audio/transcriptions and /api/v1/audio/translations accept the OpenAI format, so the OpenAI Python and JavaScript SDKs work by setting the base URL to the ToolDock API. Supported response formats are json, text, srt, vtt, and verbose_json.