K

Raon SpeechLM text-to-speech model

KraftonReleased Apr 2026.

Raon SpeechLM is a text-to-speech (TTS) model from Krafton. It ranks #85 of 103 on the Artificial Analysis TTS arena with Elo 1006 (95% CI ±13, 2,216 samples). Released Apr 2026.

Key facts

AA Elo1006±13#85 / 103
TTS Arena Elo–TTS Arena V2
ReleasedApr 2026Open weights:–
Provider
Krafton
AA rank
#85 / 103
AA Elo (95% CI)
1006 ±13
AA samples
2,216
Released
Apr 2026
Voices tested by AA
8

Not yet available: TTS Arena Elo (uncertainty), TTS Arena votes, TTS Arena win rate, Price (per 1M chars), Open weights, License, Languages, Voice cloning

Who it is for (from the data)

  • When quality is not the top priority: #85 of 103, in the bottom half; if quality matters most, check higher-ranked models first.
  • Use via Krafton's service or API; the sources do not list it as open weights.

Nearby models

By AA Elo; this model highlighted
#ModelAA EloArena EloPrice $/1M charsOpen weightsΔ
82Polly Long-Form Amazon1025–$100–+19
83RChatterbox Resemble AI10221468$25Open+16
84SLightning v3.1 Smallest.ai1022–$25–+16
85KRaon SpeechLM Krafton1006–––
86ZZonos-v0.1 Zyphra1000–$20Open-6
87MMurf Speech Gen 2 Murf AI985–$100–-21
88OOpenVoice v2 OpenVoice956–$8.3Open-50

Alternatives · Top 5 open-weight by AA Elo

#ModelAA EloArena EloPrice $/1M charsOpen weights
12Fish Audio Drama 3 Preview Fish Audio1239–$15Open
13BBreeze TTS 2 BreezeBlue1226–$34Open
22Ming-3.0-tts Ant Group1189––Open
42Fish Audio S2 Pro Fish Audio1108–$15Open
46Step Audio EditX (Mar 2026) StepFun1097––Open

How to read the scores

  • AA Elo: the Elo score from the Artificial Analysis speech arena. Listeners blind-compare two clips and pick the better one; "±" is the 95% confidence interval.
  • TTS Arena Elo: Elo from TTS Arena V2 community blind votes. The two boards use different scales, so do not subtract one from the other.
  • If the gap between two models is smaller than their combined intervals, the order is not statistically reliable; treat them as the same tier. More samples or votes mean narrower intervals.

FAQ

Where does Raon SpeechLM rank among TTS models?

As of Nov 7, 2026, Raon SpeechLM ranks #85 of 103 on the Artificial Analysis TTS leaderboard with Elo 1006 (±13).

Is Raon SpeechLM open source?

The sources do not list Raon SpeechLM as open-weight; it is generally used through the Krafton API.

Which top-10 TTS model is cheapest?

Among the AA top 10, the lowest list price is Gemini 3.8 Flash-Lite TTS (Google) at $11 per 1M characters, Elo 1254.

What is the best open-source TTS model?

By AA Elo, the top open-weight model is Fish Audio Drama 3 Preview by Fish Audio (Elo 1239, #12 overall); 18 open-weight models have an AA score.

Who makes Raon SpeechLM?

Raon SpeechLM is made by Krafton; Artificial Analysis lists its release as Apr 2026.

How reliable is Raon SpeechLM's score?

The scores are based on 2,216 Artificial Analysis samples (95% CI ±13). More samples and narrower intervals mean a more stable rank.

How far is Raon SpeechLM from #1?

#1 on Artificial Analysis is Eleven v4 (Elo 1334); Raon SpeechLM has Elo 1006, 328 points behind.

Sources

17NAS syncs the upstream leaderboards daily; this page's data was synced on Nov 7, 2026.

Price and release date come from Artificial Analysis, recorded on Oct 25, 2026.

"–" means the upstream sources do not provide this value; we do not guess.