XNews

Phonic 1 (High) Debuts at #1 on Artificial Analysis Speech to Speech Index at 87.1

Phonic 1 (High) Debuts at #1 on Artificial Analysis Speech to Speech Index at 87.1

Phonic's Phonic 1 (High) speech-to-speech model debuted at #1 on the Artificial Analysis Speech to Speech Index with a score of 87.1, narrowly ahead of Grok Voice 3.0 at 86.9. Evaluated at its high intelligence level through the Phonic API, the model ranked #1 on Tau Voice at 79.9% and #4 on Time to First Audio at 0.61 seconds, priced at $0.07 per minute or $4.20 per hour of input audio.

Event version 1.

Key insights

Top ranking on Speech to Speech Index

Phonic 1 (High) ranked #1 of 22 models on the Artificial Analysis Speech to Speech Index at 87.1, ahead of Grok Voice 3.0 at 86.9 by a very small margin. The Index averages Speech Reasoning (Big Bench Audio), Agentic Performance (Tau Voice), Arena Preference and Task Success Rate.

Clear lead on Tau Voice

Phonic 1 (High) ranked #1 on Tau Voice at 79.9%, a 5.4-point lead over the next model.

Competitive speed and cost

The model ranked #4 on Time to First Audio at 0.61 seconds and was the fastest of the top five models in the Index. It is available through the Phonic API at $0.07 per minute, or $4.20 per hour of input audio.

Speech Agent Arena results

Phonic 1 (High) ranked #8 of 30 on preference in the Speech Agent Arena with an Elo of 1012, and #4 on Task Success Rate at 92.3%.

Big Bench Audio placement

Phonic 1 (High) ranked #3 on Big Bench Audio at 98.9%, behind StepAudio 3 Realtime at 99.7% and Qwen Audio 3.0 Realtime Plus at 99.2%.

Source posts