GA Smallest AI

Smallest.ai Pulse STT

Unified STT endpoint with Pulse (multilingual, streaming) and Pulse 2.0 (English streaming with built-in end-of-turn, emotion, gender). Strong Indic and East Asian coverage, region-dependent.

Est. per minute$0.004 - 0.006

Overview

Best for: Indian-language and Asian-language voice agents that want turn detection and emotion signals.

At a glance

$/hour$0.36

Live speakersYes

Turn detectYes

PII redactYes

PartialsYes

Languages21

WebRTCNo

WebSocketYes

gRPCNo

EU dataNo

Self-hostNo

Open weightsNo

$0.006/min from the May 2026 changelog; an older page showed ~$0.004/min. 21 streaming languages, availability depends on US or India host. Hosts are US and India only. End-of-turn only on English pulse-2. Diarization and PII redaction are listed features; live support not confirmed.

Audio in

See realtime quickstart (formats not captured in this pass).

Audio out

n/a

Languages

Streaming: en, hi, de, es, ru, it, fr, nl, pt, zh, yue, ja, ko, gu, mr, or, bn, ta, te, kn, ml plus regional auto-detect groups (north_indic, multi-asian, multi-south-indic). East Asian languages US region only; South Indian languages India region only (beta).

Latency

See Pulse model card (not captured).

Regions

US (api.us.smallest.ai) and India (api.smallest.ai) hosts.

Compliance

Zero data retention documented for Enterprise plans.

Features

streaming partials
end-of-turn detection (pulse-2)
diarization
word and sentence timestamps
emotion and gender detection
PII and PCI redaction
regional auto language detection

Pricing

What	Price	Unit	Notes
Pulse streaming (WebSocket)	$0.006	per minute	Standard plan, per 2026-05-28 changelog. An older pricing page showed ~$0.004/min.
Pulse non-streaming (reference)	$0.0035	per minute

How the per-minute estimate was worked out

Changelog $0.006/min is the newest first-party figure; older page $0.004/min.

Free tier: Not captured.

Source: docs.smallest.ai

Setup

Get an API key from the Smallest console.
Open WS /waves/v1/stt/live?model=pulse (or pulse-2) on the correct regional host.
Follow the realtime quickstart for the audio format and message schema.

Endpoint

wss://api.smallest.ai/waves/v1/stt/live?model=pulse (US: wss://api.us.smallest.ai/waves/v1/stt/live)

Authentication

API key (header format not captured; see quickstart).

Warnings

Conflicting published prices

Smallest's changelog lists $0.006/min for streaming Pulse while an older pricing page shows ~$0.004/min. Confirm in your dashboard.

Region decides languages

East Asian streaming languages are US-only and South Indian ones India-only; connecting to the wrong host is rejected.

Pulse Pro is not streamable

The most accurate English model (pulse-pro) is HTTP-only; streaming requests are rejected with 400.

pulse-2 is English only

Built-in end-of-turn detection exists only on the English pulse-2 model.

Plus 12 warnings that apply to all speech-to-text, live APIs. See category warnings.

Limits

Language availability depends on region host (api.us.smallest.ai vs api.smallest.ai); wrong region returns LANGUAGE_NOT_ENABLED_IN_REGION.

Models and products

Name	Status	Notes
pulse	GA	Multilingual, streaming and pre-recorded.
pulse-2	GA	English only, streaming only, end-of-turn detection plus per-utterance emotion and gender.
pulse-pro	GA (HTTP only)	Rejected on the streaming endpoint with 400 before upgrade.

Docs and sources

Docs

Sources used

Not fully verified

Audio formats, auth header, message schema, latency, concurrency and current price. No snippet given because the protocol was not verified.

Similar speech-to-text APIs

Google CloudGoogle Cloud Speech-to-Text V2 streaming (Chirp 3)$0.004 - 0.016/min2 high-severity warnings DeepgramDeepgram Nova-3 and Flux (streaming)$0.0042 - 0.0098/min2 high-severity warnings GladiaGladia Live (Solaria-1)$0.0042 - 0.013/min1 high-severity warnings SpeechmaticsSpeechmatics Realtime and Agent STT$0.0033 - 0.013/min0 high-severity warnings

Spotted a wrong price or a dead link?