Last refresh: Nov 22, 2026
texttospeech.comGet the data

Fastest text to speech API

Updated · refreshed weekly · Methodology

Coval, our main source

Coval · time to first audio, p50, us-east-1 · read Nov 22, 2026 · 17 models measured
#ModelFirst audioCoval p50Scoreof 100Price$ / 1M chars
1Realtime TTS-2 FlashInworld59 ms58$10.42
2Simba 3.5SpeechifyAI90 ms67$15.00
3CodaRime96 ms23$50.00
4Simba 3.2SpeechifyAI101 ms87$10.00
5Simba 3.0SpeechifyAI105 ms42$10.00
6Falcon 2Murf AI141 ms57$10.00
7Realtime TTS-2Inworld161 ms70$20.83
8Eleven v4 TurboElevenLabs191 ms70$40.00
9Flash v2.5ElevenLabs200 ms36$50.00
10AssemblyAI-TTS-1AssemblyAI204 ms58$15.00

Coval: Open-source harness run every 30 minutes from us-east-1; median over a rolling 7-day window. Streaming; connection handshakes excluded; counts leading silence until the first audible sample. Showing the fastest 10.

Speko

Speko · time to first audio, p50, US East · read Nov 22, 2026 · 20 models measured
#ModelFirst audioSpeko p50Scoreof 100Price$ / 1M chars
1Realtime TTS-2 FlashInworld82 ms58$10.42
2Simba 3.2SpeechifyAI85 ms87$10.00
3Gradium TTSGradium105 ms10$47.20
4Realtime TTS-2Inworld116 ms70$20.83
5Sonic 3.6Cartesia120 ms83$49.00
6Sonic 3.5Cartesia121 ms73$49.00
7Lightning v3.1Smallest.ai173 ms17$25.00
8Fish Audio S2.1 ProFish Audio185 ms15$15.00
9Eleven v4 TurboElevenLabs205 ms70$40.00
10v3 ConversationalElevenLabs266 ms71$50.00

Speko: Sequential requests from US East, about 30 per run, re-run per model on the date shown. Showing the fastest 10.

Humanness Index

Humanness Index · time to first audio, median · read Nov 22, 2026 · 23 models measured
#ModelFirst audioHumanness Index medianScoreof 100Price$ / 1M chars
1Sonic 3.6Cartesia101 ms83$49.00
2SonicCartesia116 ms0—
3Falcon 2.1Murf AI117 ms48$10.00
4Sonic 3.5Cartesia128 ms73$49.00
5Fish Audio S2.1 ProFish Audio141 ms15$15.00
6Eleven v4 TurboElevenLabs158 ms70$40.00
7Sonic 2Cartesia159 ms3—
8Sonic 3Cartesia166 ms31$49.00
9Flash v2.5ElevenLabs197 ms36$50.00
10Neuphonic TTSNeuphonic276 ms9$20.80

Humanness Index: Region not stated. 50 sequential streaming API requests per model, measured once (the date shown). Showing the fastest 10.

Fast is not the same as good

Realtime TTS-2 Flash (Inworld) is quickest on Coval, at 59 ms, but it scores 58. The fastest model that scores 70 or more is Simba 3.2 at 101 ms (score 87).

Why the sources disagree

Coval puts Realtime TTS-2 Flash first (59 ms); Speko puts Realtime TTS-2 Flash first (82 ms); Humanness Index puts Sonic 3.6 first (101 ms).

Simba 3.2 shows the problem: Speko has it at 85 ms and Humanness Index at 428 ms, 5× apart for the same model.

The sources use different harnesses and regions, so we show them side by side and never average them. Latency is not part of the 0–100 score. Of 121 models on the leaderboard, 39 have a figure from at least one source.

Questions people ask

What is the fastest text-to-speech API?
Coval puts Realtime TTS-2 Flash first (59 ms); Speko puts Realtime TTS-2 Flash first (82 ms); Humanness Index puts Sonic 3.6 first (101 ms). Each source runs its own test, so read the table for the source you trust and do not average them.
Is the fastest TTS API also a good one?
Realtime TTS-2 Flash (Inworld) is quickest on Coval, at 59 ms, but it scores 58. The fastest model that scores 70 or more is Simba 3.2 at 101 ms (score 87).
Why do latency numbers differ between benchmarks?
Harness, region and sample size differ. Coval: Open-source harness run every 30 minutes from us-east-1; median over a rolling 7-day window. Streaming; connection handshakes excluded; counts leading silence until the first audible sample. Speko: Sequential requests from US East, about 30 per run, re-run per model on the date shown. Humanness Index: Region not stated. 50 sequential streaming API requests per model, measured once (the date shown). Simba 3.2 shows the problem: Speko has it at 85 ms and Humanness Index at 428 ms, 5× apart for the same model.

Where the numbers come from

Quality is the 0–100 score from our rank aggregation of 3 public boards: artificialanalysis.ai (Speech Arena Elo), voicearena.com (arena Elo, US English) and humannessindex.vapi.ai (humanness score 0–100). Prices are dollars per 1M characters, taken from Artificial Analysis and provider pages; per-minute prices are converted to the same unit. Latency is time to first audio (the wait before sound starts), copied from Coval, Speko and Humanness Index and never averaged across them. We do not measure anything ourselves. How latency is sourced.