Text-to-speech that carries context.
Text-to-speech purpose-built for enterprise voice agents. Expressive, low-latency TTS that handles interruptions and pauses, and carries context across the conversation. Sign up and we'll match your Flux TTS spend in credits, up to $500. Terms apply.
Every dollar you spend, matched in credits
Build with Flux TTS the way you normally would. We match your paid Flux TTS usage dollar-for-dollar, with credits added to your account weekly — up to $500 per project. Credits never expire, and you can spend them on any Deepgram API. *Restrictions apply.
Text-to-speech features
Voice agents need models that read the conversation, respond in as low as 80ms, and deploy where your data lives.
Cross-Turn Context
Tone, pacing, and emotional register persist across the whole session. No SSML, style tags, or prompt engineering required.
Ultra Low Latency
Output that starts in as low as 80ms, even under production load. Expressive range isn't sacrificed for speed.
Production-Grade Accuracy
Lowest word error rate of any read-aloud TTS tested. Pronounces alphanumerics, drug names, account numbers, dates, and currency accurately every call.
Voices Tuned for Live Conversation
Empathetic when a customer is frustrated, precise when details matter, warm across long calls.
Pricing that Scales
As low as $0.015 per 1,000 characters, with volume discounts. Predictable economics at production scale.
Flexible Deployment Options
Cloud, private cloud, or on-prem. Your processing stays in your environment for workloads like healthcare, finance, and government.
Trusted by enterprises and conversational AI leaders
Deepgram is making TTS part of the agent's conversational architecture rather than a layer developers have to tune line by line, and we're excited to bring that capability into the Pipecat ecosystem.
At jambonz, we know how important it is to build voice agents that hold up in production, especially when connecting AI applications to live phone calls. Deepgram Flux TTS tackles a problem every voice AI developer encounters: speech that flattens over the course of a conversation and forces teams into endless SSML tuning. By combining conversation-aware speech with low-latency performance and deployment flexibility, Deepgram gives teams a way to improve the caller experience without having to hand-tune every turn or give up control of their stack.
We evaluate voice agents every day at Coval, and the failure modes on the TTS side are remarkably consistent: tone that flattens by minute three, expressiveness that requires heavy SSML tuning, and inconsistency across turns that breaks the sense of a real conversation. Deepgram Flux TTS is the first model we've seen that tackles those issues directly, treating the conversation as the unit rather than the individual line. That gives voice agent teams a TTS model that can hold up under the same rigorous, scenario-based evaluation we apply to the rest of the stack, and greater confidence in how their agents will perform in production.
Making [Flux TTS] available on LiveKit's agent platform gives developers a way to add conversation-aware voice to the same real-time infrastructure they already build and deploy on.
When we first heard Alexis, we were genuinely surprised. Human, expressive, like a patient and friendly teacher. In our testing it just felt human, and for children, that matters because they have less patience and tolerance. That's why we're moving off ElevenLabs and sticking with Deepgram.
We're running 1-2k telehealth preconsult calls a day with Flux TTS, and the voice quality is genuinely the best Deepgram has shipped.
Frequently Asked Questions
Start building. We'll match every dollar.
Create a project, fund it, and get every dollar you spend on Flux TTS back in credits — up to $500.