MiniMax M3.1 Flash, DeepSeek V4.1 Flash 1017 and LightOnOCR-3-0.8B are now live. Try them now
Back to Models

Klang Pianissimo

by klang

Transcription

Description

Klang Pianissimo is Klang's open-weight Swedish speech-to-text model, a 600M-parameter fine-tune of NVIDIA Parakeet TDT 0.6B v3 with punctuation, capitalization and word-level timestamps, built for fast transcription of short clips and long recordings.

Providers

Pricing

Input$0 /1M tokens
Output$0 /1M tokens
Get Your API Key

Specifications

Context1 tokens
Parameters—
License—
ReleasedSep 2026

Capabilities

Streaming

EU-Compliant API Access

Use Klang Pianissimo with a simple API call. OpenAI-compatible endpoint, EU data residency guaranteed.

curl https://api.eurouter.pro/api/v1/audio/transcriptions \
  -H "Authorization: Bearer $EUROUTER_API_KEY" \
  -F file="@audio.mp3" \
  -F model="pianissimo-sv"

Explore more

Integrate AI without GDPR risk.

You need AI that won’t create compliance headaches. Your data stays in the EU, GDPR is enforced by default, and every request is routed for the best balance of cost, latency, and uptime, reducing risk while improving performance.

Get Your API Key
GDPR by default
EU data residency
Smart routing