Smallest AI Pulse
Model Information
Smallest AI Pulse is a multilingual speech-to-text model for both real-time streaming and pre-recorded transcription. It supports speaker diarization, keyword boosting, punctuation, code-switching, PII/PCI redaction, word-level timestamps, confidence scores, and built-in handling of background noise.
Model ID
smallestai.pulse
Use this ID when making API calls to reference this model
Provider
Smallest AI
Model Type
ASR
Accuracy Tier
premium
Supported Languages
enhideesruitfrnlptzhjakomulti-eumulti-asianmulti-indic
Automatic Language Detection: Yes
Streaming Transcription Languages
enhihi-devdeesruitfrnlptzhyuejakogumrorbntateknmlnorth_indicmulti-asianmulti-south-indic
Performance & Cost
Cost
$0.18000/hour
$0.00005/second
Processing Speed
0.004x realtime
Maximum File Size
238.42 MB
Features
Supported capabilities and functionalities
Core Features
Punctuation
Diarization
Streaming
Speaker Labels
Word Timestamps
Confidence Scores
Custom Vocabulary
Profanity Filtering
Noise Reduction
Voice Activity Detection
Subtitle Formats
SRT Support
VTT Support
Technical Specifications
Input/output formats and technical details
Subtitle Format Support
No subtitle formats supported
Supported Audio Encodings
WAVMP3FLACOpusmulawalawPCM