by xAIAudio
Grok STT
Transcripts with word timings in 25 languages
- 25 languages
From 0.01 credits per second of audio≈ $0.00
What it's like to use
Grok Speech to Text from xAI turns recordings of up to two hours into text, with automatic language detection across 25 languages, word timings, and a separate transcript per channel for split-channel calls.
Good for
- Interviews, voice notes and call recordings
- Checking a generated voice-over against its script
- Transcripts with names and numbers written your way
What Grok STT can do
Each mode opens in the studio with Grok STT already picked. The price shows before you generate.
How to prompt Grok STT
- List unusual names and brands as key terms so they're spelled the way you want.
- For calls recorded with each side on its own channel, switch multichannel on; otherwise one side can go missing.
- Turn on text normalization to get prices and dates written as $1,250 or March 14.
Settings worth knowing
Everything else has a sensible default, so you can type a prompt and go.
audio_url- The voice or music track to use.
language25- The language of the speech.
How it compares
Same kind of job, different strengths and prices.
HeartMuLa Transcribe is tuned for sung lyrics over music; Grok handles spoken audio.
Questions about Grok STT
How much does Grok STT cost?
On PopNow, the cheapest run of Grok STT costs 0.01 credits ($0.00) per second of audio. You pay with credits (1 credit = $0.01), the exact cost shows on the Generate button before you start, and failed generations are refunded automatically.
What can Grok STT do?
On PopNow, Grok STT works in these modes: Speech to Text. Pick one in the studio and add a prompt or an upload.
How should I write prompts for Grok STT?
List unusual names and brands as key terms so they're spelled the way you want. For calls recorded with each side on its own channel, switch multichannel on; otherwise one side can go missing. Turn on text normalization to get prices and dates written as $1,250 or March 14.
Grok STT or HeartMuLa Transcribe?
HeartMuLa Transcribe is tuned for sung lyrics over music; Grok handles spoken audio.
Do I need to install anything to use Grok STT?
No. Grok STT runs in your browser on PopNow: write a prompt or add a file, choose the settings and download the result. Sign up and you can generate straight away.
Make something with Grok STT
Type an idea, pick your settings and see the price before you hit Generate.