AA Provider Voice TTS Arena ↗Unversioned · provider native voices
1,173.34Provider native voices · all categories · US + UK accents · 8 listed voices
95% CI 1,162.34–1,184.34 · n=4,989
fal-aiReleased Feb 14, 2026
MiniMax Speech 2.8 [HD]
Use timed pause tags, a custom pronunciation dictionary, and separate pitch, energy and timbre controls for narration.
Source description
Generate speech from text prompts and different voices using the MiniMax Speech-2.8 HD model, which leverages advanced AI techniques to create high-quality text-to-speech.
Provider endpoints2
Benchmark results1
Measured performance
All leaderboards ↗Benchmark results
Access & cost
2 quotesPrices across providers
Model specifications
- Developer
- fal-ai
- Modality
- Audio
- Context
- Not reported
- Maximum output
- Not reported
- Weights
- Not reported
- Released
- Feb 14, 2026
- Provider listed
- Feb 4, 2026
- First discovered
- Oct 16, 2026
Exact identities
- openrouter
minimax/speech-2.8-hd - fal
fal-ai/minimax/speech-2.8-hd - aa-tts
1a91c803-1508-4c8e-9327-e05d09b0cfc8
Sources
Updated Oct 18, 2026
More from fal-ai
View all ↗fal-aiListed Sep 8
Elevenlabs - Forced Alignment
Align the transcript and your audio recording using Elevenlab's forced alignment feature!
No reported score
No reported score
Price not listed
fal-aiListed Jun 17
Ltx 2.3 Quality
Text to Audio high-quality using LTX-2.3 with Lora
No reported score
No reported score
Price not listed
No reported score
Price not listed
fal-aiListed Jun 16
Zonos2 Text to Speech
Zonos2 is a text-to-speech model that clones a voice from a short sample and speaks naturally across many languages.
No reported score
No reported score