Skip to main content Latency Metrics Time-to-First-Transcript (TTFT) Our Pulse STT model provides State of the art TTFT latency of ~64ms , which is one of the least in the world.
TTFT (Time to First Transcript) measures the latency between when a user stops speaking and when the model returns the complete transcript. Lower TTFT means faster response times and better user experience in real-time applications. Model Latency (ms) Smallest Pulse STT 64 Deepgram Nova 2 76 Deepgram Nova 3 71 Assembly AI Universal 698
Accuracy Metrics Word Error Rate (WER) All models were evaluated on the FLEURS dataset, a standardised multilingual speech benchmark ensuring fair cross-model comparison.
Language WER English 5.1% Italian 4.2% Spanish 5.4% Hindi 11.4%
Throughput Requests Per Second Audio Length HTTP POST Short (< 5s) 50-100 Medium (5-30s) 20-50 Long (30s+) 10-20
Throughput varies based on audio length, format, and server load Linear16 (PCM)
Latency : Lowest (~64ms)Accuracy : HighestBandwidth : HighestBest for : High-quality applications
Opus
Latency : Low (~70-80ms)Accuracy : HighBandwidth : LowBest for : Browser/mobile applications
FLAC
Latency : Medium (~80-90ms)Accuracy : HighestBandwidth : MediumBest for : Archival/quality-critical use cases
μ-law
Latency : Low (~65-75ms)Accuracy : GoodBandwidth : LowestBest for : Telephony applications
Italian : 4.2% WER, ~64ms latencyEnglish : 5.1% WER, ~64ms latencySpanish : 5.4% WER, ~64ms latencyPortuguese : 7.1% WER, ~64ms latencyGerman : 8.5% WER, ~64ms latencyFrench : 9.2% WER, ~64ms latency
Regional Variations
Indian Languages : 10-15% WER, ~90-100ms latencyEastern European : 9-12% WER, ~85-95ms latency
Diarization
Latency Impact : +10-20msAccuracy Impact : MinimalUse When : Multiple speakers present
Word Timestamps
Latency Impact : +5-10msAccuracy Impact : NoneUse When : Timing information needed
Emotion Detection
Latency Impact : +15-25msAccuracy Impact : NoneUse When : Emotion analysis required
Optimization Tips
Use 16kHz sample rate for optimal balance
Choose linear16 format for lowest latency
Enable only needed features to reduce latency
Batch process when latency isn’t critical
Next Steps 
