FluffyStack toolsJurisdictional exposure
Attributes
- SLA Uptime
- 99.9%
- Streaming
- Yes
Sub-services (4)
Chirp Universal Model
2B-parameter speech model supporting 125+ languages with unified weights
Streaming Recognition
Low-latency bidirectional streaming API for real-time transcription
Batch Recognition
Async long-form transcription for audio files up to 8 hours
Speech Adaptation
Phrase hints and boost values to bias recognition to domain terms
Compliance & Certifications
This service is attested for the following frameworks. Always verify with the provider before relying on a specific compliance posture.
Where this runs
Sovereign regions (1)
- T-Systems Sovereign Cloud · FrankfurtT-Systems Sovereign Cloud powered by Google Cloud
Commercial regions (43)
Europe (13)
- Belgium
- Finland
- Paris
- Berlin
- Frankfurt
- Milan
- Turin
- Netherlands
- Warsaw
- Madrid
- Stockholm
- Zurich
- London
North America (12)
- Montréal
- Toronto
- Querétaro
- Northern Virginia
- Columbus
- Iowa
- Dallas
- Las Vegas
- Los Angeles
- South Carolina
- Salt Lake City
- Oregon
South America (2)
- São Paulo
- Santiago
Asia (10)
- Hong Kong
- Delhi
- Mumbai
- Jakarta
- Osaka
- Tokyo
- Singapore
- Seoul
- Taiwan
- Bangkok
Oceania (2)
- Melbourne
- Sydney
Middle East (3)
- Tel Aviv
- Doha
- Dammam
Africa (1)
- Johannesburg
Tags
Equivalent services on other platforms
Automatic speech recognition service with real-time streaming and batch transcription across 100+ languages, speaker diarisation, custom vocabulary, PII redaction, and specialised Transcribe Medical and Transcribe Call Analytics flavours
Prebuilt and customisable AI APIs (formerly Azure AI Services/Cognitive Services) for speech, translation, language, vision, Custom Vision, Document Intelligence, Content Understanding and Content Safety, with Entra ID auth and container options.
Unified speech service: real-time and batch speech to text in 100+ languages with diarisation, neural text to speech with 600+ voices and custom voice, and speech translation. Speaker recognition was retired on 30 September 2025.
Speech-to-text transcription with word-level timestamps, speaker diarisation, profanity filtering, and custom-vocabulary support. Synchronous and asynchronous-batch modes; 30+ languages.