ai/list101

ElevenLabs Scribe v3

elevenlabs.io

Transcribe recorded audio into speaker-labeled text with timestamps, terminology prompts and language and number-formatting controls.

Ai AudioDeveloper Tools
Visit website
Screenshot of ElevenLabs Scribe v3 official website
Pricing
Freemium
Available on
Web, API
Category
Ai Audio

What is ElevenLabs Scribe v3?

ElevenLabs Scribe v3 converts recorded speech into text through the website and API, with availability for data-residency workspaces requiring confirmation. It serves creators processing interviews and podcasts, teams working with meeting recordings, and developers adding transcription to applications. Scribe v3 Live is the separate model for real-time audio.

The website accepts audio or video files and provides manual transcript editing and export options. API users can select how numbers appear and supply secondary language hints for recordings that contain more than one language.

Key features

Speaker labels and timestamps

Diarization separates up to 32 speakers, while word-level timestamps connect transcript text to the recording.

Terminology prompting

Supply up to 1,000 batch keyterms, each up to 50 characters, to guide recognition of names, acronyms and specialist vocabulary.

Language and number controls

Support covers more than 90 languages. API controls let you provide secondary languages and request numbers as digits or words.

Audio-event tagging

Optionally label non-speech events such as laughter and applause when creating a website transcript.

Review and export

Play audio from a selected transcript word, manually correct the transcript, rename speakers and export the results.

Who is it for?

Podcast producers preparing transcripts

Create a speaker-labeled draft of an episode for editorial review.

Teams documenting recorded meetings

Turn a meeting recording into text that participants can review and reference.

Developers processing audio archives

Integrate recorded-file transcription into an application using the API.

How to use ElevenLabs Scribe v3

  1. Confirm that Scribe v3 is available in your workspace, especially if you require data residency.
  2. Open Speech to Text in the ElevenLabs dashboard, select Transcribe files and upload an audio or video file.
  3. Choose a primary language or automatic detection, optionally enable audio-event tags and add keyterms, then submit.
  4. Review the transcript against playback, manually correct text or speaker names, and export the result.
  5. For application integration, create an API key, install an SDK and submit a batch Speech to Text request using model ID scribe_v3.

ElevenLabs Scribe v3 pricing

Freemium

Limited free transcription is available alongside paid plans. API payment options include subscriptions and pay-as-you-go, with recorded-audio transcription metered by audio hour. Keyterm prompting and automated API transcript editing carry additional charges. Included usage and concurrency depend on the plan; prices exclude taxes, levies and duties.

Check current pricing ↗

What to know before you use it

  • Scribe v3 handles recorded audio; real-time integrations use Scribe v3 Live. Transcription preserves the spoken language rather than translating it.
  • Customers with data-residency requirements should confirm Scribe v3 availability for their workspace. The help center identifies Scribe v2 for residency workspaces, while the launch announcement offers regional enterprise Scribe v3 environments.
  • Keyterm prompting and automated API transcript editing incur additional charges. Automated editing through transcript_edit is experimental and unavailable in data-residency environments; it is a separate feature from manual website corrections.
  • Website uploads have a maximum file size of 3 GB for audio or video.

Frequently asked questions

Can I upload a video instead of extracting its audio?

Yes. The website accepts both audio and video files for transcription, subject to its 3 GB upload limit.

Can the API normalize transcript formatting?

Yes. Number controls select digits or words. Separately, experimental automated editing through transcript_edit accepts natural-language instructions for date or unit formatting, carries an additional charge and is unavailable in data-residency environments.

Which model ID selects recorded-audio Scribe v3?

Use scribe_v3 in the API. It is the website's default Speech to Text model outside the residency exception described by the help center. Confirm availability with ElevenLabs if your workspace requires data residency.

ElevenLabs Scribe v3 alternatives

Scribe v3 Live

Choose this model for live audio applications requiring conversational turn prediction.