TechPrufer
Get started
Together AI
Together AI logoTogether AI · Feature trail

Text-to-Speech (TTS) Model Deployment

7 posts · Dec 2025 – Feb 2026

What this trail covers

Together AI now offers native deployment of elite proprietary Text-to-Speech (TTS) models, including Rime's Arcana v2 and Mist v2, on dedicated infrastructure. This enables high-quality, low-latency voice generation with advanced features like deterministic pronunciation control, multilingual support, and conversational realism. The integration allows for co-location with LLM and STT workloads for a unified real-time voice agent pipeline, offering a single API, authentication, and observability surface. Mist v2 provides deterministic pronunciation control, ensuring consistent rendering of defined terms across all voices and channels, crucial for high-volume production environments. Arcana v2 offers expressive, conversational voices trained on real customer service interactions. Both models are available on dedicated endpoints with a 99.9% uptime SLA and compliance certifications (SOC 2 Type II, HIPAA ready, PCI compliant).

All Together AI trails
  1. Rime Arcana V3 Turbo and Rime Arcana V3 now available on Together AIThis post introduces Rime Arcana V3 Turbo and Rime Arcana V3 to the Together AI platform. V3 Turbo offers English-Spanish code-switching with ~120ms time-to-first-audio on dedicated endpoints, trained on bilingual speech patterns to maintain cadence and prosody. V3 supports code-switching across 11 languages with ~160ms time-to-first-audio. Both models are co-located with LLM and STT workloads, providing a unified API, authentication, and observability surface. The performance of V3 Turbo enables higher concurrency per GPU, reducing TCO for high-volume bilingual deployments. V3 consolidates multilingual support into a single model, simplifying infrastructure for international call centers and regulated services.
  2. MiniMax Speech 2.6 Turbo now available natively on Together AIThis post announces the native deployment of MiniMax Speech 2.6 Turbo on Together AI's dedicated infrastructure. Key technical contributions include achieving sub-250ms latency, supporting 40+ languages with streaming inline switching, 10-second voice cloning, and automatic emotional awareness. The integration with LLM and STT workloads on the same infrastructure is highlighted as a key benefit for reducing cross-vendor overhead and enabling real-time conversational latency as an infrastructure guarantee. The post also details the production infrastructure benefits, including isolated GPU capacity, a 99.9% uptime SLA, SOC 2 Type II, HIPAA readiness, and zero data retention.
  3. Rime voice models now available on Together AIThis post announces the addition of Rime's Arcana v2 and Mist v2 proprietary TTS models to the Together AI platform. It details their capabilities, including Arcana v2's expressivity and multilingual support, and Mist v2's deterministic pronunciation control. The post highlights the benefits of co-locating these TTS models with LLM and STT workloads on Together AI's dedicated GPU endpoints for reduced latency and unified management. It emphasizes production-grade latency (225ms p50 time-to-first-audio for Mist v2), conversational realism through training on real customer service calls, and proven scalability. Use cases for global contact centers, real-time customer service, healthcare, and voice banking are presented. The underlying production infrastructure, including dedicated GPU capacity, uptime SLAs, compliance, and developer experience features like unified SDKs and observability, is also described.