Soniox
tts-rt-v2
Measured 2026-07-03
Naturalness
~1606
Win % · 95% CI
—
Drift
18
Synth p50
381ms
381–417 p50–p90
Robustness
0.78
Fined:
• minor · dates — said “slash” out loud; a prompt fixes this (8 of 14 transcripts)
→ we sent “Renewal falls on 1/1/2027.”
→ it said “Renewal falls on one slash one slash 27.”
• serious · dates — said “slash” out loud (8 of 14 transcripts)
→ we sent “The policy started 11/30/2024.”
→ it said “The policy started. Eleventhirty slash twenty twenty four.”
• minor · dates — said “slash” out loud; a prompt fixes this (8 of 14 transcripts)
→ we sent “The deadline moved to 10/02.”
→ it said “The deadline moved to ten slash zero two.”
• minor · dates — said “slash” out loud; a prompt fixes this (11 of 30 transcripts)
→ we sent “Your slot is 03/09 this year.”
→ it said “Your slot is zero three slash zero nine this year.”
• minor · dates — said “slash” out loud; a prompt fixes this (8 of 14 transcripts)
→ we sent “Renewal is 02/29/2024.”
→ it said “Renewal is zero two slash 29 slash 2,024.”
• minor · dates — said “slash”, “zero seven slash” out loud; a prompt fixes this (11 of 23 transcripts)
→ we sent “Your appointment is on 07/15/2026.”
→ it said “Your appointment is on zero seven slash fifteen slash two thousand twenty six.”
• minor · dates (international, ×0.4) — said “dash” out loud; a prompt fixes this (3 of 11 transcripts)
→ we sent “The order shipped on 2026-03-09.”
→ it said “The order shipped on twenty twenty six dash zero three -nine.”
• minor · dates (international, ×0.4) — said “slash” out loud; a prompt fixes this (6 of 11 transcripts)
→ we sent “The lease ends 2025/06/30.”
→ it said “The lease ends 2025 slash zero six slash thirty.”
• minor · math operators — kept the value but never said “minus”; a prompt fixes this (13 of 23 transcripts)
→ we sent “That leaves 10-4=6 remaining.”
→ it said “That leaves ten to four equals six remaining.”
Cost / 1M chars
~$13.0
Token-billed: $4/1M text in, $21.50/1M audio out; the vendor states ~$0.70 per hour of generated speech (soniox.com/pricing). At 900 chars/min (54,000 chars/hour) that is ~$13 per 1M chars. Unchanged from v1 — the pricing page now lists only TTS v2 at the same rates.
Share this result
Embed the live badge
[](https://benchmarks.speko.ai/tts/soniox-tts-rt-v2)
<a href="https://benchmarks.speko.ai/tts/soniox-tts-rt-v2"><img src="https://benchmarks.speko.ai/badge/tts/soniox-tts-rt-v2.svg" alt="Speko tts rank"></a>
https://benchmarks.speko.ai/tts/soniox-tts-rt-v2