Inworld Realtime TTS-2 claims the #1 spot on Artificial Analysis's streaming TTS leaderboard at a 70% lower cost than the next best model.
Inworld Realtime TTS-2 has achieved the #1 ranking for streaming text-to-speech on Artificial Analysis while being 70% cheaper than its closest competitor. The model supports context-aware synthesis, natural-language voice steering (such as prompt-based emotion and tone adjustments), sub-130ms latency, and multilingual output. Inworld is offering a 50% discount for new sign-ups this month to capitalize on its leaderboard success.
Inworld's aggressive pricing combined with high quality disrupts the text-to-speech market, putting direct pressure on premium players like ElevenLabs.
* Top ranking on independent benchmarks validates Inworld's quality claims.
* Substantially lower pricing makes high-volume voice agent applications economically viable for developers.
* Features like conversational context awareness and natural-language steering indicate a shift towards more expressive and interactive voice agents.
DISCOVERED
2h ago
2026-06-15
PUBLISHED
3h ago
2026-06-15
RELEVANCE
AUTHOR
inworld_ai