Text to speech API speed test: Speakvora vs Amazon Polly vs Google (November 2026)
Disclosure: I run Speakvora. This is our own test, run from one MacBook with the same code for every voice. The Speakvora voices ran on our Mac mini; Polly and Google were reached over the internet, so part of our lead i
Disclosure: I run Speakvora. This is our own test, run from one MacBook with the same code for every voice. The Speakvora voices ran on our Mac mini; Polly and Google were reached over the internet, so part of our lead is distance. Details and caveats are below.
If you are building a voice agent, two numbers matter first: how long until the first sound plays, and how bad the slow end is (the 95th percentile). We measured both, for one caller and for four callers at once.
Results
Time to the first audible sound, in milliseconds. Lower is better.
| Voice | 1 caller, median | 1 caller, 95th | 4 callers, median | 4 callers, 95th |
|---|---|---|---|---|
| Speakvora Phonon | 41 | 51 | 42 | 52 |
| Speakvora Pocket | 79 | 89 | 104 | 118 |
| Amazon Polly Standard | 83 | 103 | 73 | 97 |
| Amazon Polly Generative | 203 | 222 | 205 | 227 |
| Google Standard | 352 | 434 | 339 | 476 |
| Google Chirp 3 HD | 1,055 | 1,558 | 1,064 | 1,530 |
How we measured
- One MacBook, one program, the same five sentences for every voice. Each caller kept one connection open, as an app would, after two untimed warm-up requests.
- Every request counted. No errors, refusals or timeouts happened in any row.
- First sound means the first audio bytes plus any silence at the start of the audio, the way Coval defines time to first audio. It is our own implementation of their description.
- One caller made 20 requests and four callers made 10 each. These are small samples, so read the 95th percentile as approximate.
What this does not show
- Our voices ran on a Mac mini on the same network as the test computer, over Wi-Fi through an encrypted tunnel. Polly and Google were reached over the internet. We expect our times to change a little on a wired connection and will update.
- Google's text to speech returns the whole clip at once, so its number is the time for the entire sentence, not a streaming start.
- Voice quality is not part of this test. Listen before you choose.
- Our voices come from a smaller catalog than the big providers, and there is no uptime guarantee yet.
Full table and method
The whole table, the method, and a ten-minute capacity test (25 + 10 + 2 live callers on one Mac mini with no errors) are on our speed page: https://speakvora.com/performance
The API itself costs $3 per million characters, with 100,000 characters free: https://speakvora.com/text-to-speech
Originally published at https://speakvora.hashnode.dev/text-to-speech-api-speed-test-speakvora-vs-amazon-polly-vs-google-november-2026
Originally published by Dev.to WebDev. Aggregated on AIWithGhost for educational purposes — full credit and traffic to the original publisher.