Step Audio EditX (Mar 2026) text-to-speech model

StepFunOpenCNReleased Feb 2026.

Step Audio EditX (Mar 2026) is a text-to-speech (TTS) model from StepFun. It ranks #41 of 98 on the Artificial Analysis TTS arena with Elo 1100 (95% CI ±12, 2,359 samples). Weights are openly available for self-hosting. Released Feb 2026.

Key facts

AA Elo1100±12#41 / 98
TTS Arena Elo–TTS Arena V2
Price (per 1M chars)–USD
ReleasedFeb 2026Open weights:Yes
Provider
StepFun
AA rank
#41 / 98
AA Elo (95% CI)
1100 ±12
AA samples
2,359
TTS Arena Elo (uncertainty)
–
TTS Arena votes
–
TTS Arena win rate
–
Price (per 1M chars)
–
Released
Feb 2026
Open weights
Yes
License
–
Voices tested by AA
2
Languages
–
Voice cloning
–

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

Nearby models

By AA Elo; this model highlighted
#ModelAA EloArena EloPrice $/1M charsOpen weights
38Fish Audio S2 Pro Fish Audio1110–$15Open
39RChatterbox HD Resemble AI1110–$40–
40TTS-1 HD OpenAI1103–$30–
41Step Audio EditX (Mar 2026) StepFun1100––Open
42Turbo v2.5 ElevenLabs10991497$50–
43HSpeech 2.6 Hithink10971491––
44Multilingual v2 ElevenLabs10961500$100–

Alternatives · More from StepFun

#ModelAA EloArena EloPrice $/1M charsOpen weights
15StepAudio 2.5 TTS (Aug 2026) StepFun1214–$85–
32Step TTS 2 (Mar 2026) StepFun1140–$40–

Alternatives · Top 5 open-weight by AA Elo

#ModelAA EloArena EloPrice $/1M charsOpen weights
9Fish Audio Drama 3 Preview Fish Audio1248–$15Open
11BBreeze TTS 2 BreezeBlue1230–$34Open
19Ming-3.0-tts Ant Group1191––Open
38Fish Audio S2 Pro Fish Audio1110–$15Open
46Voxtral TTS Mistral1091–$16Open

FAQ

Where does Step Audio EditX (Mar 2026) rank among TTS models?

As of Oct 25, 2026, Step Audio EditX (Mar 2026) ranks #41 of 98 on the Artificial Analysis TTS leaderboard with Elo 1100 (±12).

Is Step Audio EditX (Mar 2026) open source?

Yes. Step Audio EditX (Mar 2026) has open weights and can be self-hosted.

What is the best Chinese TTS model?

By AA Elo, the top model from a Chinese provider is Qwen-Audio-3.1-TTS-Plus by Alibaba (Elo 1307, #3 overall).

Which top-10 TTS model is cheapest?

Among the AA top 10, the lowest list price is Simba 3.2 (SpeechifyAI) at $6.6 per 1M characters, Elo 1246.

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 1248, #9 overall); 18 open-weight models have an AA score.

Sources

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