Left is faster. Higher reads more hard parts right.
ElevenLabs Flash v2.5 is better on non-streaming latency. Deepgram Aura-2 is better on streaming latency, stopping, accuracy, naturalness and price.
Last updated Methodology by Dileep Chagam
Measure by measure, the same sentences, the same place.
An estimate: speech-to-text transcribers scored it, not people.
The same sentence, read by each voice.
ElevenLabs Flash v2.5. ElevenLabs Flash v2.5: 182 ms. Deepgram Aura-2: 281 ms.
ElevenLabs Flash v2.5. ElevenLabs Flash v2.5: 182 ms. Deepgram Aura-2: 281 ms.
Deepgram Aura-2. ElevenLabs Flash v2.5: 177 ms. Deepgram Aura-2: 126 ms.
Deepgram Aura-2. ElevenLabs Flash v2.5: Finishes first. Deepgram Aura-2: 40 ms.
Deepgram Aura-2. ElevenLabs Flash v2.5: 64.4%. Deepgram Aura-2: 77.2%.
Deepgram Aura-2. ElevenLabs Flash v2.5: $40.00. Deepgram Aura-2: $30.00.