Utility model

Fikra Speech-to-Text

fikra-stt

livealias

Transcribe supported audio into text via the /v1/audio/transcriptions endpoint.

Published rate

$0.001 / minute

Prices last changed 2026-11-04. If this page and /v1/models disagree, the API is correct and this page is a bug.

Routing and retention

Model type

Stable Fikra alias for a third-party model

Upstream family

utility

Retention

Prompts are not used for training. Response bodies may be cached for up to 300 seconds for non-ZDR requests. A ZDR request disables that cache. Upstream retention varies by provider; the model page lists the provider.

This ID is kept for compatibility. New clients should read the model page and use the public model name where possible.

Call it

OpenAI-compatible. One line changes.

from openai import OpenAI

client = OpenAI(base_url="https://api.fikraapi.co.ke/v1", api_key="fk_...")

response = client.chat.completions.create(
    model="fikra-stt",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Try it first

A playground is available for chat models. The quote endpoint returns a price before you run a call.

Open playground

Quote endpoint ->

Need a key? Start with $0.50 credit.