Measurements
How we measure our voices.
We publish numbers we took ourselves, with the date and the method. Results are mixed: no system leads every column. A human blinded listen is still pending.
“Target” figures are goals we have not measured yet, not results. Anything marked “Measured” is a number we took ourselves; your latency depends on network, region and text length. First audio is the time to the first non-empty response body, including the network, not a verified start of playback.
10 November 2026
Same-harness results, one client, one text set.
Apart from the row marked Staging, the seven entries come from an eight-arm parallel run, each with the English voice selected by a pre-declared automatic rule: the highest mean automatic wideband predicted-MOS score among up to three candidates (phone score as a tie-break). The Staging row is a separate run later the same day; it is not available on the public API yet. Latency is client-observed over 129 calls per entry: the median and the 95th percentile. Naturalness figures are automatic MOS estimates, not a human listening test. A human blinded listen is pending.
| System | First audio, median | First audio, p95 | Full clip, median | Word error | Predicted MOS, wide / phone |
|---|---|---|---|---|---|
| ElevenLabs (1 of 3) | 0.145 s | 0.159 s | 0.229 s | 6.51% | 4.37 / 3.93 |
| VoxVain Aria, staging path2 Staging | 0.209 s | 0.283 s | 0.302 s | 6.51% | 4.51 / 4.21 |
| VoxCore (Aria)1 | 0.160 s | 0.226 s | 0.181 s | 6.51% | 4.51 / 4.21 |
| Deepgram | 0.175 s | 0.241 s | 2.820 s | 6.85% | 4.43 / 3.91 |
| ElevenLabs (2 of 3) | 0.202 s | 0.296 s | 1.346 s | 6.51% | 4.28 / 3.15 |
| xAI TTS | 0.250 s | 0.342 s | 0.805 s | 5.94% | 4.28 / 3.69 |
| OpenAI | 0.552 s | 0.890 s | 1.516 s | 6.85% | 4.48 / 4.01 |
| ElevenLabs (3 of 3) | 0.636 s | 0.760 s | 2.046 s | 6.74% | 4.35 / 3.45 |
1 VoxCore is the production phone-path service. In this test it returned a complete WAV file, not a stream, and it is not the path the public API serves today. 2 The Staging row is the Aria voice on VoxCore, streamed through a staging copy of the VoxVain API route. It is not available on the public API yet; billing integration and review are in progress. This row is a separate run on 10 November (about 1:20–1:40 PM ET) with the same client, texts, harness and scorers, run on its own rather than alongside the other systems, with the phrase cache off and requests paced about 2.2 s apart; its word error was scored on CPU instead of GPU. The 0 request errors refer to that accepted run of 129 requests; an earlier unpaced attempt hit the per-key rate limit and was discarded. The three ElevenLabs rows are three of their public systems, in first-audio-median order; model and pack names are omitted.
Date: 10 November 2026. Client: one host in US East. Text: the same 43 English lines used on 1 November (4,732 characters, 876 normalized words). Connection: one persistent keep-alive HTTPS session per system; one warmup line per voice was paid and discarded. First audio is time from sending the request to the first non-empty response-body chunk, including the network. Full clip is time to the last byte. Latency n = 129 (three passes of the 43 lines) for each entry, 0 request errors. Quality n = 43; for the parallel-run entries, these were also the voice-selection lines. Predicted MOS is an automatic score, reported on wideband audio and on an 8 kHz phone-channel copy. Word error is an automatic corpus rate after an English text normalizer. Predicted MOS and word error are automatic scores; the method is described on this page. The client machine was under heavy load during the parallel run, which can add noise to every system in it. Systems in this table: three from ElevenLabs; Deepgram; xAI TTS; OpenAI; the VoxCore phone path; and VoxVain Aria through a staging API route. No competitor audio is published here. A human blinded listen of this set is pending.
How to read this. No system leads every column. On this client and text set, an ElevenLabs system had the lowest measured first-audio median (0.145 s, against 0.209 s for Aria through the staging API route); VoxCore had the lowest measured full-clip median (0.181 s); xAI TTS had the lowest measured word-error rate among the entries shown (5.94%); the two VoxVain Aria GPU paths, the VoxCore phone path and the staging path, had the highest rounded predicted-MOS results shown, both 4.51 wideband / 4.21 phone (unrounded, the VoxCore phone path is 4.513 / 4.206 and the staging path 4.512 / 4.207). Those are automatic scores, not a human preference result.
Earlier measurement · 1 November 2026
Aria against five ElevenLabs systems, on localhost.
This is a dated earlier comparison, kept for the record. It used the same 43 lines and automatic scorers, but Aria’s speed was measured on the test node’s localhost as a complete file, not on the public API. It is not the current same-harness result; see the 10 November table above.
| Metric | VoxVain Aria | ElevenLabs A | ElevenLabs B | ElevenLabs C | ElevenLabs D | ElevenLabs E |
|---|---|---|---|---|---|---|
| Predicted MOS, wideband | 4.512 | 4.347 | 4.280 | 4.360 | 4.437 | 4.451 |
| Predicted MOS, phone channel | 4.205 | 3.894 | 3.207 | 3.484 | 3.974 | 4.102 |
| Word error rate, lighter scorer, phone % | 6.74 | 5.59 | 5.94 | 6.51 | 6.16 | 5.94 |
| Word error rate, heavier scorer, phone % | 7.08 | 4.57 | 5.94 | 5.37 | 5.25 | 6.16 |
| Entity error %, small / medium | 0.0 / 1.27 | 1.27 / 0.0 | 0 / 0 | 0 / 0 | 0 / 0 | 0 / 0 |
| First audio p50 / p90, seconds | 0.115 / 0.136* | 0.134 / 0.148 | 0.174 / 0.232 | 0.497 / 0.557 | 0.403 / 0.464 | 0.357 / 0.498 |
n = 43 lines (4,732 characters). Latency n = 129 (three passes). The ElevenLabs A–E columns are five of their public systems, in the original column order; model, pack and voice names are omitted. An automatic judge on 12 lines, both orders: Aria edged ElevenLabs A (3 wins, 1 loss, 8 ties); ElevenLabs B led Aria (7–1–4); the A/A control was 12 ties. Predicted MOS is an automatic score, not a human MOS. These are automatic scores; the method is described on this page. *Aria latency is a complete, non-streamed file on localhost. Over a network it would be slower; we did not measure that path in this run. An earlier same-harness test from our box, 4 October 2026, had Aria 0.21 s and an ElevenLabs system 0.19 s to first audio.
How to read this. Aria led the automatic naturalness scores, especially on a phone-band copy, and had the lower localhost first-audio median in this set. Every ElevenLabs system had a lower word-error rate. The then-newest of the five in this test, ElevenLabs B, was preferred by the automatic judge. This mixed result is not a human listen and is not a public-API latency test.
List prices, 10 November 2026
Our list prices next to other providers.
Each figure is from the provider's public pricing page, fetched 10 November 2026. Minutes are not packaged identically, so read what each one includes. We are not the lowest in every column.
| Provider | Speech, per 1,000 characters | Streaming transcription, per minute | Voice agent, per minute | Phone, per minute | Number, per month |
|---|---|---|---|---|---|
| VoxVain | $0.012 | $0.0052 | $0.048, conversation model included | $0.015 in / $0.019 out | $1.59 per additional number |
| ElevenLabs | $0.04 | $0.0037 | $0.08 | n/a | n/a |
| Cartesia | $0.037 to $0.065 | $0.0065 | $0.03 plus the language model | $0.014 on a Cartesia number | n/a |
| Deepgram | $0.015 and $0.030 | $0.0077 | $0.075 | n/a | n/a |
| OpenAI | $0.015 | $0.017, $0.003 batch | $0.05 | n/a | n/a |
| Vapi | pass-through | pass-through | $0.05 hosting plus providers | pass-through | n/a |
| Retell | pass-through | included | $0.07 to $0.31 | $0.015 | $2.00 |
| Synthflow | n/a | n/a | Annual contract, no public rate | n/a | n/a |
Sources, fetched 10 November 2026: ElevenLabs, Cartesia, Deepgram, OpenAI, Vapi, Retell, Synthflow; AssemblyAI and Murf figures on Pricing: AssemblyAI, Murf. VoxVain prices are for customers subscribing from 10 November 2026. PlayHT closed on 31 December 2025 and is not listed. Plans and allowances are on Pricing.
How we test
The rules for a number we will stand behind.
Within each test on this page, every system is measured with the same text, the same client, and the same clock. Latency is client-observed time to the first non-empty response body, including the network. Naturalness scores are a predicted MOS from an automatic scorer, not a human rating. The method is described on this page. We do not publish a single-winner claim, and a human blinded listen of the 10 November set is still pending.
This page is not Bench + Sim, which is our agent-testing product. List prices live on Pricing. We do not treat vendor marketing latency, or a public arena ranking, as our measurement.
Start building with VoxVain.
Get a free API key in a minute, no card needed. Then follow the quickstart.