VibeVoice 1.5B text-to-speech model
MicrosoftOpenReleased Aug 2025.
VibeVoice 1.5B is a text-to-speech (TTS) model from Microsoft. It ranks #83 of 98 on the Artificial Analysis TTS arena with Elo 956 (95% CI ±14, 2,160 samples). Weights are openly available for self-hosting. Released Aug 2025.
Key facts
- Provider
- Microsoft
- AA rank
- #83 / 98
- AA Elo (95% CI)
- 956 ±14
- AA samples
- 2,160
- TTS Arena Elo (uncertainty)
- –
- TTS Arena votes
- –
- TTS Arena win rate
- –
- Price (per 1M chars)
- –
- Released
- Aug 2025
- 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| # | Model | AA Elo | Arena Elo | Price $/1M chars | Open weights |
|---|---|---|---|---|---|
| 80 | KRaon SpeechLM Krafton | 1006 | – | – | – |
| 81 | ZZonos-v0.1 Zyphra | 1000 | – | $20 | Open |
| 82 | MMurf Speech Gen 2 Murf AI | 988 | – | $100 | – |
| 83 | VibeVoice 1.5B Microsoft | 956 | – | – | Open |
| 84 | OOpenVoice v2 OpenVoice | 955 | – | $8.3 | Open |
| 85 | NNeuphonic TTS Neuphonic | 943 | – | $20.8 | – |
| 86 |  Qwen3 TTS Flash Alibaba | 942 | – | $11 | – |
Alternatives · More from Microsoft
| # | Model | AA Elo | Arena Elo | Price $/1M chars | Open weights |
|---|---|---|---|---|---|
| 30 | Azure HD 2.5 Microsoft | 1143 | – | $22 | – |
| 74 | Azure Neural Microsoft | 1034 | – | $15 | – |
| 77 | MAI-Voice-1 Microsoft | 1030 | – | – | – |
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 VibeVoice 1.5B rank among TTS models?
As of Oct 25, 2026, VibeVoice 1.5B ranks #83 of 98 on the Artificial Analysis TTS leaderboard with Elo 956 (±14).
Is VibeVoice 1.5B open source?
Yes. VibeVoice 1.5B 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.