Pulse Pro
Model: Pulse Pro · smallest.ai
—
Response time · transcription only
Smallest AI's Pulse beats Deepgram Nova-3 on 7 of 8 Open ASR Leaderboard datasets, averaging 5.42% WER versus Nova-3's 8.60%, with ~64ms time-to-first-token. Deepgram offers a lower per-minute price; Pulse leads on accuracy, latency, and compliance (SOC 2, HIPAA, GDPR, ISO 27001) for real-time voice agents.
Deepgram
Model: Nova 3
—
Response time · transcription only
Pulse Speech-to-Text
Real-time transcription with industry-leading accuracy and ~64ms time-to-first-token, built for live voice agents.
30+ Languages
Accurate transcription across 30+ languages, with native English performance ranked #2 on the Open ASR Leaderboard.
Enterprise-Grade Compliance
SOC 2 Type II, GDPR, ISO 27001, and HIPAA-ready — with a Business Associate Agreement available for healthcare deployments.
Features
Benchmarks
Benchmark
▼
WER % on the Hugging Face ESB benchmark (9 English datasets, streaming). Lower is better. Pulse is competitive on aggregate and leads on meeting/noisy audio; AssemblyAI leads on clean read speech. Source: HF ESB, internal evaluation.
Frequently
asked questions
Can Pulse STT run on-premise?
Does Deepgram support emotion recognition?
How does Pulse STT's latency compare to Deepgram Nova-3?
What does switching from Deepgram to Pulse STT involve?