Ming-3.0-tts text-to-speech model

Ant GroupOpenCNReleased Oct 2026.

Ming-3.0-tts is a text-to-speech (TTS) model from Ant Group. It ranks #19 of 98 on the Artificial Analysis TTS arena with Elo 1191 (95% CI ±14, 2,169 samples). Weights are openly available for self-hosting. Released Oct 2026.

Key facts

AA Elo1191±14#19 / 98
TTS Arena Elo–TTS Arena V2
Price (per 1M chars)–USD
ReleasedOct 2026Open weights:Yes
Provider
Ant Group
AA rank
#19 / 98
AA Elo (95% CI)
1191 ±14
AA samples
2,169
TTS Arena Elo (uncertainty)
–
TTS Arena votes
–
TTS Arena win rate
–
Price (per 1M chars)
–
Released
Oct 2026
Open weights
Yes
License
–
Voices tested by AA
3
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
16Gemini 3.1 Flash TTS Google1213–$18.3–
17VLuna TTS VUI Labs1210–$15–
18CSonic 3.5 Cartesia1192–$49–
19Ming-3.0-tts Ant Group1191––Open
20Fish Audio S2.1 Pro (Oct 2026) Fish Audio1186–$15–
21Eleven v3 ElevenLabs11841498$100–
22SSoniox TTS Real-Time v2 Soniox1182–$14.2–

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
38Fish Audio S2 Pro Fish Audio1110–$15Open
41Step Audio EditX (Mar 2026) StepFun1100––Open
46Voxtral TTS Mistral1091–$16Open

FAQ

Where does Ming-3.0-tts rank among TTS models?

As of Oct 25, 2026, Ming-3.0-tts ranks #19 of 98 on the Artificial Analysis TTS leaderboard with Elo 1191 (±14).

Is Ming-3.0-tts open source?

Yes. Ming-3.0-tts 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.