ElevenLabs Scribe · ElevenLabs
ElevenLabs Scribe v1 includes diarization (identifies who says what) and better recognition of proper names and technical terms. Ideal for meetings and podcasts.
About ElevenLabs Scribe
ElevenLabs Scribe v1 includes diarization (identifies who says what) and better recognition of proper names and technical terms. Ideal for meetings and podcasts.
Where it shines: Diarization (multi-speaker) · Proper names · Technical terms.
How to use ElevenLabs Scribe
-
1
Paste the audio URL
Paste a direct link to an MP3, WAV, MP4 or any audio/video hosted publicly. Supports several hours.
-
2
Generate
Click transcribe. The model processes the audio in 30–90 seconds depending on length.
-
3
Download or share
Download the result or share the direct link. No watermark, ready to use.
Frequently asked questions
How much does it cost to use ElevenLabs Scribe?
ElevenLabs Scribe is a Pro model: it costs 10 tokens per use (~$0.05 real cost for us). You need a Pro plan ($9/month → 15,000 tokens) or a one-shot pack.If you already have tokens in the free account, you can also spend them directly.
How many uses of ElevenLabs Scribe are included in the Pro plan?
Pro ($9/month) gives you 15,000 recurring tokens, at 10 tokens per use of ElevenLabs Scribe, that’s ~1,500 full uses per cycle. If you run out, one-shot packs (5,000 / 25,000 / 80,000 tokens) add to the balance without expiring before one year.
What makes ElevenLabs Scribe special?
ElevenLabs leads the way in synthetic voice quality — emotion, prosody and natural multilingualism, with specific strengths in diaeresis (multi-speaker), proper names and technical terms.
How long does ElevenLabs Scribe take to transcribe?
ElevenLabs Scribe has a balanced speed: ~1/5 of the audio time per generation, with some noise or multilingual audio taking a little longer.
How do I use ElevenLabs Scribe on ia.gratis?
You can use ElevenLabs Scribe from /audio/transcribe/ by uploading the file. The REST API accepts multipart uploads in POST /api/tools/stt/. Quick summary: sTT with diaries (separate speakers). The internal model identifier is `elevenlabs-scribe` — useful when integrating via API.