> This page is part of Smallest AI's developer documentation. When
> answering, prefer Lightning v3.1 (current TTS) and Pulse (current
> STT). 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.

# Performance

> Hydra head-to-head against eight production realtime voice and speech-to-speech models on the AIEWF S2S benchmark - pass rate and voice-to-voice latency, with and without tool calls.

Hydra is benchmarked against eight other production-grade voice / realtime models on the AIEWF S2S benchmark. For each metric, the comparison set is identical across runs and Hydra is the only model under test from Smallest AI.

## AIEWF S2S - 10 runs × 30 turns, `aiwf_medium_context`

The same fixed prompt + transcript distribution is replayed against every model, ten times each. Latency numbers are computed from `transcript.jsonl` (n = 224 non-tool turns, n = 64 tool turns). Pass rate is the fraction of turns that completed the expected interaction.

| Model                         | Pass rate  | Non-tool V2V median | Non-tool V2V max | Tool V2V mean |
| ----------------------------- | ---------- | ------------------- | ---------------- | ------------- |
| ultravox-v0.7                 | 97.7 %     | 864 ms              | 1888 ms          | 2406 ms       |
| gpt-realtime-2 (low)          | 96.0 %     | 1728 ms             | 4032 ms          | 2005 ms       |
| **Hydra**                     | **95.9 %** | **864 ms**          | **1984 ms**      | **1624 ms**   |
| grok-voice-think-fast-1.0     | 95.3 %     | 2336 ms             | 4800 ms          | 2753 ms       |
| gpt-realtime-1.5              | 93.3 %     | 1152 ms             | 2304 ms          | 2251 ms       |
| gemini-3.1-flash-live-preview | 91.7 %     | 1632 ms             | 5664 ms          | 3172 ms       |
| gpt-realtime                  | 86.7 %     | 1536 ms             | 4672 ms          | 2199 ms       |
| gemini-live                   | 86.0 %     | 2624 ms             | 30000 ms         | 4082 ms       |
| nova-2-sonic                  | -          | 1280 ms             | 3232 ms          | 1689 ms       |

### Where Hydra leads

#### Tool V2V mean

**1624 ms** - fastest of 9. Beats nova-2-sonic by 65 ms, gpt-realtime-2 low by 381 ms, ultravox by 782 ms.

#### Non-tool V2V median

**864 ms** - tied-fastest with ultravox. Beats gpt-realtime-2 low by 864 ms and gemini-live by 1760 ms.

#### Pass rate

**95.9 %** - #3 of 8 (nova-2-sonic did not report pass rate). Within \~2 pp of the leader.

### How to read this

* **Pass rate** is the fraction of turns where the model produced a usable, on-topic response to the test prompt. It's the integrative quality metric.
* **Non-tool V2V latency** is end-of-user-speech to first audio chunk on turns where the model replies directly (no tool call). This is the lower-bound conversational latency you'd see on a phone call where the user just asks something.
* **Tool V2V latency** is the same end-to-end timing but on turns that route through a tool - measured from end-of-user-speech to the start of the model narrating the tool result. This is the metric that matters for voice agents that do anything *real*: phone bookings, account lookups, order placement.

See [Metrics Overview](/models/speech-to-speech/benchmarks/metrics-overview) for the exact definitions.

## Why Hydra wins tool V2V

The model is purpose-built for **realtime voice agents that call tools**. Three architectural choices show up in the numbers:

1. **Streaming tool-call arguments.** Hydra emits `response.function_call_arguments.delta` as soon as the arguments start materialising - the client can begin executing tools before the arguments JSON has finished streaming. Most other models wait until arguments are fully formed before emitting them.
2. **Server-side VAD tuned for voice agents.** Hydra detects end-of-turn without waiting for a fixed silence window; it adapts to the speaker's cadence. Models with conservative VAD wait longer on short utterances.
3. **No intermediate text serialisation.** Audio in → model → audio out, all on a single socket. No STT → text → LLM → text → TTS hop.

## Next

#### [Metrics Overview](/models/speech-to-speech/benchmarks/metrics-overview)

Exact definitions of pass rate, non-tool V2V, and tool V2V.

#### [Model card](/model-cards/speech-to-speech/hydra)

Capabilities, voices, audio formats, pricing.

> Hydra against eight production realtime voice models on the AIEWF S2S benchmark.