Higgs Audio V3 TTS text-to-speech model
Boson AIOpenReleased Jun 2026.
Higgs Audio V3 TTS is a text-to-speech (TTS) model from Boson AI. It ranks #69 of 98 on the Artificial Analysis TTS arena with Elo 1045 (95% CI ±13, 2,234 samples). List price is about $15 per 1M characters. Weights are openly available for self-hosting. Released Jun 2026.
Key facts
- Provider
- Boson AI
- AA rank
- #69 / 98
- AA Elo (95% CI)
- 1045 ±13
- AA samples
- 2,234
- TTS Arena Elo (uncertainty)
- –
- TTS Arena votes
- –
- TTS Arena win rate
- –
- Price (per 1M chars)
- $15
- Released
- Jun 2026
- Open weights
- Yes
- 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 |
|---|---|---|---|---|---|
| 66 | AAsync Flash v1.0 async | 1050 | – | $10.1 | – |
| 67 | MMaya 2 Global Maya Research | 1050 | – | – | – |
| 68 | MMaya1 Maya Research | 1048 | 1401 | – | Open |
| 69 | BHiggs Audio V3 TTS Boson AI | 1045 | – | $15 | Open |
| 70 |  OpenAudio S1 Mini Fish Audio | 1045 | – | $15 | Open |
| 71 |  Gemini 2.5 Pro (Dec 2025) Google | 1040 | – | $18.3 | – |
| 72 | HOctave TTS Hume AI | 1039 | 1517 | $87.5 | – |
Alternatives · Cheaper with AA Elo ≥ 1015
| # | Model | AA Elo | Arena Elo | Price $/1M chars | Open weights |
|---|---|---|---|---|---|
| 8 | Gemini 3.8 Flash-Lite TTS Google | 1252 | – | $11 | – |
| 10 | SSimba 3.2 SpeechifyAI | 1246 | – | $6.6 | – |
| 12 | IRealtime TTS-2 Flash Inworld | 1219 | – | $10.4 | – |
| 13 |  Voxtral 3 TTS Mistral | 1219 | – | $13 | – |
| 22 | SSoniox TTS Real-Time v2 Soniox | 1182 | – | $14.2 | – |
Alternatives · Top 5 open-weight by AA Elo
| # | Model | AA Elo | Arena Elo | Price $/1M chars | Open weights |
|---|---|---|---|---|---|
| 9 | Fish Audio Drama 3 Preview Fish Audio | 1248 | – | $15 | Open |
| 11 | BBreeze TTS 2 BreezeBlue | 1230 | – | $34 | Open |
| 19 |  Ming-3.0-tts Ant Group | 1191 | – | – | Open |
| 38 | Fish Audio S2 Pro Fish Audio | 1110 | – | $15 | Open |
| 41 |  Step Audio EditX (Mar 2026) StepFun | 1100 | – | – | Open |
FAQ
Where does Higgs Audio V3 TTS rank among TTS models?
As of Oct 25, 2026, Higgs Audio V3 TTS ranks #69 of 98 on the Artificial Analysis TTS leaderboard with Elo 1045 (±13).
Is Higgs Audio V3 TTS open source?
Yes. Higgs Audio V3 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.