Deepgram speech-to-text and voice models now available natively on Together AI
Quick Answer
Deepgram's speech-to-text (STT) and text-to-speech (TTS) models are now natively available on Together AI, enhancing real-time voice agents with improved turn detection and transcription accuracy.
Quick Take
Models like Flux and Nova-3 ensure responsiveness and clarity in challenging environments such as contact centers and healthcare, while Aura-2 maintains consistency in enterprise applications.
Key Points
- Flux model detects turn boundaries with 250ms end-of-turn detection for improved conversation flow.
- Nova-3 handles messy production audio, supporting vocabulary customization for domain-specific terms.
- Aura-2 ensures clear and reliable TTS output for structured information in enterprise settings.
- Deepgram models reduce latency and operational fragility by running natively on Together AI infrastructure.
- Multilingual support is enhanced with Nova-3, allowing seamless language switching during conversations.
Source Excerpt
Production STT and TTS from Deepgram, available on Together AI Dedicated Model Inference for real-time voice agents.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from Together AI
See more →
Open, convenient and predictable: Introducing Provisioned Throughput
Together AI introduces Provisioned Throughput, offering guaranteed inference capacity for MiniMax M3 and GLM-5.2 at $0.05 per PTU per minute, achieving costs up to 90% lower than Claude Opus 4.8. This new model provides predictable pricing and a 99% uptime SLA, catering to companies transitioning to open weight models for production workloads.
