> This page is part of Smallest AI's developer documentation. When
> answering, prefer Lightning v3.1 (current TTS) and Pulse (current
> multilingual STT) — or Pulse 2.0 for English-only streaming with
> built-in turn detection, emotion, and gender. Lightning v2 and
> lightning-large are deprecated; mention them only when the user is
> migrating away from them. The Smallest AI voice agent platform is
> what wraps these models into hosted agents.

# Model Cards

## Docs

- [Compare models](https://docs.smallest.ai/model-cards/compare.md): Every Smallest AI model on one page. What goes in, what comes out, latency, languages, transport and pricing, with links to each model card.
- [Benchmarks](https://docs.smallest.ai/model-cards/benchmarks.md): All Smallest AI model benchmarks in one place: Lightning text to speech, Pulse speech to text, and Hydra speech to speech, with a page per benchmark.
- [Lightning v3.1 Pro](https://docs.smallest.ai/model-cards/text-to-speech/lightning-v-3-1-pro.md): Model card for Lightning v3.1 Pro. Premium 44.1 kHz TTS pool with a curated voice catalog across American, British, and Indian accents, English + Hindi code-switching, 31 supported languages plus `auto` routing, and improved naturalness.
- [Lightning v3.1](https://docs.smallest.ai/model-cards/text-to-speech/lightning-v-3-1.md): Model card for Lightning v3.1. High-fidelity, low-latency text-to-speech at 44 kHz with voice cloning, streaming, and 20 supported language codes plus `auto` routing.
- [TTS Evaluation Script](https://docs.smallest.ai/model-cards/text-to-speech/tts-evaluation-script.md): WebSocket-based evaluation script for measuring Lightning v3.1 TTFB and audio quality.
- [Pulse 2.0](https://docs.smallest.ai/model-cards/speech-to-text/pulse-2-0.md): Model card for Pulse 2.0, Smallest AI's English-only streaming speech-to-text model with built-in end-of-turn detection, per-utterance emotion, and speaker gender.
- [Pulse Pro](https://docs.smallest.ai/model-cards/speech-to-text/pulse-pro.md): Model card for Pulse Pro. High-accuracy English speech-to-text positioned #2 on the public Open ASR Leaderboard. Pre-recorded only, HTTP transport.
- [Pulse](https://docs.smallest.ai/model-cards/speech-to-text/pulse.md): High-accuracy, low-latency speech-to-text model built for real-time transcription across a broad language set, with regional aggregators and both streaming and non-streaming support.
- [Electron](https://docs.smallest.ai/model-cards/llm/electron.md): Model card for Electron - Smallest AI's in-house language model. OpenAI-compatible chat completions, 70 languages with first-class Indic support, voice-agent-optimized tool calling, prefix caching.
- [Hydra](https://docs.smallest.ai/model-cards/speech-to-speech/hydra.md): Model card for Hydra - Smallest AI's full-duplex speech-to-speech model. Audio in, audio out, one WebSocket. Built for phone-grade latency and barge-in.