
Benchmarks12 min read
Coval TTS benchmark: Gepard vs 25 APIs
We ran Gepard 1.0 through Coval's public TTS harness against its 25 listed APIs. 68.7 ms to first audio, 20.5 ms of leading silence, 0 errors in 30 samples.
Read the postReproducible measurements of text-to-speech latency, accuracy and audio quality, including metrics no other vendor publishes.

We ran Gepard 1.0 through Coval's public TTS harness against its 25 listed APIs. 68.7 ms to first audio, 20.5 ms of leading silence, 0 errors in 30 samples.
Read the post
Four vendors, both transports, 240 measured calls, zero errors. Gepard returns first audio in 49 to 50 ms over WebSocket, about half the next fastest.
Read the post
Ten realtime voice vendors in one table. ElevenLabs Flash is $50 per million characters, Cartesia $30, ours $5. Here is what that means on your monthly bill.
Read the post