← Back to all models
Scribe v2 (Speech to Text)
ElevenLabs · speech-to-text-v2
ElevenLabs' state-of-the-art transcription: 90+ languages, word-level timestamps, speaker diarization and audio-event tagging.
Starting price
57,904
per hour
Billing
Pay as you go
Service status
Active
About Scribe v2 (Speech to Text)
ElevenLabs' state-of-the-art transcription: 90+ languages, word-level timestamps, speaker diarization and audio-event tagging.
Scribe v2 (Speech to Text) pricing
Billed on the seconds of your input audio
| Quantity | Price |
|---|---|
| per hour(default) | 57,904 |
| per minute | 965 |
| per second | 16 |
One rate per unit — no separate input, output, cache or token charges.
Model id
Provider
Inputs
Outputs
Billing basis
Status
Share model
Sample code and API for Scribe v2 (Speech to Text)
Point the base URL at CupAI and use your own API key; the rest of the request stays exactly as it is in any compatible client.
View the model documentationcurl 'https://api.cupai.ir/v1/audio/transcriptions' \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer $CUPAI_API_KEY' \
-d '{
"model": "speech-to-text-v2",
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
}'Replace CUPAI_API_KEY with your own key.
Create an API key
Capabilities
Capabilities supported by this model's API.
audio-to-text
Frequently asked questions about Scribe v2 (Speech to Text)
- How is using Scribe v2 (Speech to Text) charged?
- This model is billed by the duration of the audio, not by tokens: one rate per second of audio, quoted on this page per minute or per hour. The rate is in the price table on this page and is deducted from your wallet.
- How do I connect to Scribe v2 (Speech to Text)?
- Point the base URL at CupAI, put your API key in the request header, and send the model id in the request body. Ready-made samples are on this page.
- How do payments work?
- Payments are in Toman and need no foreign credit card. Credit you buy can be spent on any available model.
Other models
How model pricing works
Every AI model strikes a different balance between speed, answer quality and cost. Flagship models suit complex reasoning, long-document analysis and precise code generation, while lighter models cost considerably less for summarising, classification and short answers. The list above shows each model's rate broken down by input token, output token and cache, so you can estimate the cost of your workload before you start.
A token is the smallest unit of text a model processes; roughly speaking a thousand tokens is about 750 English words. The cost of a request is the sum of its input and output tokens, so shortening your prompt and capping the response length reduces cost directly. Some models have a second price tier for very long inputs, which reprices the entire request once it crosses a stated threshold.