Left is faster. Higher reads more hard parts right.
ElevenLabs Flash v2.5 is better on non-streaming latency, naturalness and price. Deepgram Flux is better on streaming latency, stopping and accuracy.
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 Flux: 194 ms.
ElevenLabs Flash v2.5. ElevenLabs Flash v2.5: 182 ms. Deepgram Flux: 194 ms.
Deepgram Flux. ElevenLabs Flash v2.5: 177 ms. Deepgram Flux: 154 ms.
Deepgram Flux. ElevenLabs Flash v2.5: Finishes first. Deepgram Flux: 80 ms.
Deepgram Flux. ElevenLabs Flash v2.5: 64.4%. Deepgram Flux: 77.4%.
ElevenLabs Flash v2.5. ElevenLabs Flash v2.5: $40.00. Deepgram Flux: $45.00.