Multilingual v2 text-to-speech model
ElevenLabsReleased Aug 2023.
Multilingual v2 is a text-to-speech (TTS) model from ElevenLabs. It ranks #44 of 98 on the Artificial Analysis TTS arena with Elo 1096 (95% CI ±10, 7,520 samples). On TTS Arena V2 it scores Elo 1500 (±23, 1,173 votes). List price is about $100 per 1M characters. Released Aug 2023.
Key facts
- Provider
- ElevenLabs
- AA rank
- #44 / 98
- AA Elo (95% CI)
- 1096 ±10
- AA samples
- 7,520
- TTS Arena Elo (uncertainty)
- 1500 ±23
- TTS Arena votes
- 1,173
- TTS Arena win rate
- 51.7%
- Price (per 1M chars)
- $100
- Released
- Aug 2023
- Open weights
- –
- License
- –
- Voices tested by AA
- 8
- Languages
- –
- Voice cloning
- –
"–" means the upstream sources do not provide this value; we do not guess.
Nearby models
By AA Elo; this model highlighted| # | Model | AA Elo | Arena Elo | Price $/1M chars | Open weights |
|---|---|---|---|---|---|
| 41 | 1100 | – | – | Open | |
| 42 | 1099 | 1497 | $50 | – | |
| 43 | HSpeech 2.6 Hithink | 1097 | 1491 | – | – |
| 44 | 1096 | 1500 | $100 | – | |
| 45 | 1092 | 1495 | $60 | – | |
| 46 | 1091 | – | $16 | Open | |
| 47 | 1089 | – | $15 | – |
Alternatives · Cheaper with AA Elo ≥ 1066
| # | Model | AA Elo | Arena Elo | Price $/1M chars | Open weights |
|---|---|---|---|---|---|
| 1 | 1336 | – | $40 | – | |
| 2 | 1332 | – | $80 | – | |
| 3 | 1307 | – | $19.3 | – | |
| 4 | CSonic 3.6 Cartesia | 1292 | – | $49 | – |
| 5 | 1280 | – | $16.5 | – |
Alternatives · More from ElevenLabs
| # | Model | AA Elo | Arena Elo | Price $/1M chars | Open weights |
|---|---|---|---|---|---|
| 1 | 1336 | – | $40 | – | |
| 2 | 1332 | – | $80 | – | |
| 14 | 1215 | – | $50 | – | |
| 21 | 1184 | 1498 | $100 | – | |
| 42 | 1099 | 1497 | $50 | – |
Alternatives · Top 5 open-weight by AA Elo
| # | Model | AA Elo | Arena Elo | Price $/1M chars | Open weights |
|---|---|---|---|---|---|
| 9 | 1248 | – | $15 | Open | |
| 11 | BBreeze TTS 2 BreezeBlue | 1230 | – | $34 | Open |
| 19 | 1191 | – | – | Open | |
| 38 | 1110 | – | $15 | Open | |
| 41 | 1100 | – | – | Open |
FAQ
Where does Multilingual v2 rank among TTS models?
As of Oct 25, 2026, Multilingual v2 ranks #44 of 98 on the Artificial Analysis TTS leaderboard with Elo 1096 (±10).
Is Multilingual v2 open source?
The sources do not list Multilingual v2 as open-weight; it is generally used through the ElevenLabs API.
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
- Artificial Analysis TTS leaderboard ↗
- TTS Arena V2 (TTS-AGI, Hugging Face) ↗
- Model page (as listed on TTS Arena) ↗
"–" means the upstream sources do not provide this value; we do not guess.