Official documentation
Speech to Text (ElevenLabs documentation)
ElevenLabs, 2026
Read the originalRead on October 17, 2026
- What it is
- ElevenLabs' documentation page for its Speech to Text API. It describes billing by audio duration, file limits, keyterm prompting and the Scribe v2 models.
- How much weight it carries
- Vendor documentation for the vendor's own product. It describes features and limits as of the date read, and it can change. Prices are on a separate page.
Facts taken from this source
- ElevenLabs says Scribe v2 supports keyterm prompting with up to 1,000 terms.
“Accurate transcription in 90+ languages Keyterm prompting, up to 1000 terms” (Models: Scribe v2)
- ElevenLabs bills its speech to text service by how long the audio is that you send for transcription.
“ElevenLabs charges for speech to text based on the duration of the audio sent for transcription.” (How does billing work for the speech to text API?)
- ElevenLabs says that files up to 3 GB in size are supported by its speech to text API.
“Files up to 3 GB in size are supported.” (FAQ)
- ElevenLabs says that keyterm prompting and transcript editing come at an additional cost, on top of the base transcription rate.
“Keyterm prompting and transcript editing come at an additional cost.” (Advanced features)
- ElevenLabs says keyterm prompting is available with Scribe v2, Scribe v2 Medical in batch mode, and Scribe v2 Realtime.
“Keyterm prompting is available with Scribe v2, Scribe v2 Medical (batch), and Scribe v2 Realtime.” (Keyterm prompting)