Grok Bot template · Content & Publishing
Speech to text (transcriptions and captions)
Shared by Jeroen
Transcribes audio and video into timed SRT captions. Uses AssemblyAI for burnable captions and OpenRouter for cheaper text or Whisper timestamps
What this Grok bot does
Transcribes audio and video into timed SRT captions. Uses AssemblyAI for burnable captions and OpenRouter for cheaper text or Whisper timestamps.
Speech to text (transcriptions and captions) at a glance
Speech to text (transcriptions and captions) is an on demand content bot shared by Jeroen and first listed on 2026-10-08. It works when you message it rather than on a timer, which keeps usage low. 3 independent public catalogs list it, and its x.ai share link was last checked live on 2026-10-20.
How Speech to text (transcriptions and captions) compares
On our popularity score (installs, votes and how many catalogs list it), Speech to text (transcriptions and captions) shares rank 669 of 1,120 Content & Publishing bots with 111 others.
| Bot | What it does | Schedule · access | Compared with Speech to text (transcriptions and captions) |
|---|---|---|---|
| Speech to Motion Video@krog_420 | Turns any speech or voice clip into a finished motion-graphics video with animated UI, infographics, kinetic… | On demandHigh access | Both cover speech, video and text. It asks for more access (publishing) and also connects to X (Twitter). |
| Scriptopher Nolan, Video Content Producer@Ortix008 | Turns your ideas into tight, hook-first 6-15 second video scripts with beats, timed voiceover and on-screen… | On demandLow access | Both cover video, timed and text. Same schedule and access level. |
| Voice Clone@sia14u | Clones voices from samples and turns any text into natural speech, delivering audio files right in chat | On demandLow access | Both cover text, speech and audio. Same schedule and access level. |
Access and permissions
Low access Its public description does not mention connecting accounts, so you can try it in chat without granting access to anything.
No account access mentioned in the public description.
Derived from the public description. The live configuration on x.ai is the source of truth — review it before adding.
Before you add Speech to text (transcriptions and captions)
- Keep publishing behind a manual approval step until you trust the bot's judgment.
- Open the x.ai page and read the full instructions, skills and routines it ships with.
Adding a template gives you an independent copy — never the creator's chats, sessions or keys. How adding a Grok Bot template works.