Inworld launches Realtime TTS-2 and TTS-2 Flash
Start here
Inworld released two realtime text-to-speech models, Realtime TTS-2 and Realtime TTS-2 Flash, both in preview. The company says the first audio arrives in as little as 90 ms for TTS-2 and 50 ms for Flash. TTS-2 covers about 500 languages and dialects and accepts plain-language delivery instructions; Flash gives up expressive steering for lower latency and cost. Pricing starts at $7 per million characters for Flash on the Growth plan. On demand, TTS-2 is $25 per million characters, falling to $15 at $300 per month and $12.50 at $1,500 per month; Flash is $15, falling to $7. Inworld cites Coval benchmarks showing Flash reaches first audio up to 3x sooner than ElevenLabs and up to 35x sooner than OpenAI GPT-4o mini TTS. It also offers an OpenAI-compatible endpoint and an ElevenLabs migration tool.
Generated from reports · updated 10 h ago
Report timeline
Follow the reports to see the event from different sides.
- Hacker News · AIInworld launches Realtime TTS-2 and TTS-2 Flash with first audio as low as 50 ms
Inworld released two realtime text-to-speech models, Realtime TTS-2 and Realtime TTS-2 Flash, with first audio as low as 90 ms and 50 ms respectively. Realtime TTS-2 covers about 500 languages and dialects and accepts plain-language delivery instructions, while Flash trades expressive steering for latency and cost, priced from $7 per million characters on the Growth plan. Inworld cites Coval benchmarks putting Flash up to 3x sooner to first audio than ElevenLabs and up to 35x sooner than OpenAI GPT-4o mini TTS, and offers an OpenAI-compatible endpoint plus an ElevenLabs migration tool.
Heat for this event
- Current, comparable range
- 7
- Peak, comparable range
- 10November 19 17:00
- Change in 24 hours
- –
The trend compares the same participants over hours observed continuously, so its range can be narrower than the current heat count. Hover or tap the chart for hourly heat; the arrow keys move through it.