About Any Video to Text

A free tool that turns a video link or a recording into text. Paste a TikTok, YouTube, Instagram, Facebook or X link, or drop an audio or video file, and get the transcript with timestamps.

Who runs it

Any Video to Text (anyvideototext.com) is built and run by Charbel Daccache, an independent developer who builds data and transcription tools. It launched in October 2026. Questions, bugs and ideas go straight to him: hello@anyvideototext.com.

How a transcript is made

• Video links: when the video has captions (added by the creator or the platform), we use them as they are. When it doesn't, the audio is transcribed by Whisper, an open speech recognition model, run by Groq or DeepInfra.
• Files you upload: your browser pulls out the audio and sends only that, compressed, in 10-minute pieces. The file itself never leaves your device.
• Speaker labels: when you ask for them, the recording is transcribed by AssemblyAI, which tells voices apart, and deleted there as soon as the transcript is back.
• Summaries: a language model writes them from the transcript only.

What it costs

Free: 5 a day, no sign-up. Credits (no subscription): $5 for 200, $15 for 1,000, $39 for 5,000. 1 credit is one transcript of up to 10 minutes; failed videos are never charged. See pricing.

What we keep

We never download or store the videos. Transcripts of public videos are kept for 30 days so the next request for the same video is instant. Uploaded files, their audio and their transcripts are not stored. The details are in the privacy policy.

Use it from your AI assistant

The same tool is available as an MCP server for Claude, ChatGPT and Cursor.