Sign up to get early access.
Inworld’s world-class voice models are coming to the EU
Expressive voices, cloning, rich multilingual support, realtime streaming, and emotion plus non-verbal controls for $5 per million characters. European data centers with full GDPR compliance.
Trusted by
Try our TTS for yourself
138/1000
Features
Ultra-low latency across Europe
EU data centers keep traffic in-region, delivering sub-250 ms response times for realtime conversational AI.
Multilingual
Deliver native-quality speech in major European languages such as Spanish, French, German, Italian, and more.
Regulatory compliance made easy
Fully GDPR compliant with controls that help teams meet local security and privacy requirements.
Built-in redundancy
Distributed infrastructure in Europe to provide high availability, automatic failover, and consistent performance across the region
Ultra-low latency across Europe
EU data centers keep traffic in-region, delivering sub-250 ms response times for realtime conversational AI.
Multilingual
Deliver native-quality speech in major European languages such as Spanish, French, German, Italian, and more.
Regulatory compliance made easy
Fully GDPR compliant with controls that help teams meet local security and privacy requirements.
Built-in redundancy
Distributed infrastructure in Europe to provide high availability, automatic failover, and consistent performance across the region
Pricing
Two powerful models with radically accessible pricing.
Inworld-TTS-1
$5/1M characters ~$0.005/minute
Inworld-TTS-1-Max
$10/1M characters ~$0.01/minute
Latest
See our most recent case studies, blog posts, and product updates.