Microsoft MAI-Voice-1
Listed Proprietary · Microsoft
2.8
/100
Microsoft MAI-Voice-1 is a proprietary text-to-speech (TTS) API from Microsoft, measured by one independent benchmark, Artificial Analysis.
Artificial Analysis
Amazon Polly Long-Form Amazon · text-to-speech (TTS) API
ListedSpeech Arena Elo 1,031 on Artificial Analysis, latency not measured; ranked 97th (tied) of 112 in the TTS for Voice Agents 2026 index.
Benchmark summary: 2.8/100, ranked 97th (tied) of 112 in the TTS for Voice Agents 2026 index (Listed). Strongest criterion: voice quality, 2.6 of 20 points.
Amazon Polly Long-Form is a proprietary text-to-speech (TTS) API from Amazon, measured by one independent benchmark, Artificial Analysis.
Overall score
2.8 /100
Score breakdown
- Real-time speed 0 /60
- Voice quality 2.6 /20
- Accuracy 0 /15
- Price 0.2 /5
Data checked on September 30, 2026
Updated after each benchmark capture
Every point comes from a public benchmark: sources · methodology
Amazon Polly Long-Form ranks 97th of 112 in the 2026 text-to-speech (TTS) API benchmark, with a score of 2.8/100.
Real-time latency
Neither Coval nor Speko measures Amazon Polly Long-Form's latency, so it scores 0 of 60 on real-time speed and does not appear in the real-time ranking.
Accuracy (word error rate)
No accuracy measurement: Coval does not measure its word error rate and Speko does not rate its pronunciation robustness, so accuracy counts 0 of 15.
Voice quality
In the Artificial Analysis Speech Arena (capture of October 1, 2026), Amazon Polly Long-Form has an Elo of 1,031 (±13, 95% confidence) from 1,893 blind comparisons, 68th highest of the 92 models Artificial Analysis rates.
Price
Artificial Analysis lists Amazon Polly Long-Form at $100 per 1M characters (69th lowest of the 78 models Artificial Analysis lists a price for).
Scoring note
Artificial Analysis changed its Speech Arena Elo between the captures of September 30, 2026 and October 1, 2026 without a new measurement date (1,032, then 1,031): the score uses the average, 1,031.5. The value shown is the latest.
Benchmark measurements
Artificial Analysis Speech Arena
- Speech Arena Elo (blind listener preference)
- 1,031
- Elo 95% interval (±)
- 13
- Arena rank
- 68
- Arena rank range
- 62-73
- Arena appearances
- 1,893
- Voices tested
- 3
- Price per 1M characters
- 100 USD
- Released
- Nov 2023
- Artificial Analysis model
- Polly Long-Form
- Artificial Analysis leaderboard
- artificialanalysis.ai
Not collected
- Speed (Coval time to first audio) — not measured by Coval (capture of 2026-10-01, 30-day window); counts 0
- Speed (Speko time to first audio) — not measured by Speko (capture of 2026-10-01); counts 0
- Quality (Speko naturalness) — not measured by Speko (capture of 2026-10-01); counts 0
- Accuracy (Coval word error rate) — not measured by Coval (capture of 2026-10-01, 30-day window); counts 0
- Accuracy (Speko robustness) — not measured by Speko (capture of 2026-10-01); counts 0
- Price (Speko cost per 1M characters) — not measured by Speko (capture of 2026-10-01); counts 0
Similar TTS models
Alibaba Qwen3 TTS
Listed Proprietary · Alibaba (Qwen)
3.1
/100
Alibaba Qwen3 TTS is a proprietary text-to-speech (TTS) API from Alibaba (Qwen), measured by one independent benchmark, Artificial Analysis.
Artificial Analysis
StyleTTS 2
Listed Open weights · StyleTTS
3.1
/100
StyleTTS 2 is an open-weights text-to-speech (TTS) API from StyleTTS, measured by one independent benchmark, Artificial Analysis.
Artificial Analysis