Smallest AI provides APIs for text-to-speech, speech-to-text, and voice agents.
Deepgram
Deepgram provides APIs for speech-to-text, text-to-speech, and voice agents for real-time voice applications.

About Deepgram
Deepgram provides APIs for speech-to-text, text-to-speech, voice agents and audio intelligence, aimed at developers and businesses building real-time voice applications. Its Flux models are described as conversation-aware, handling turn-taking, interruptions and conversational context, and the platform can be used in real time or in batch, in the cloud or self-hosted. A unified Voice Agent API combines speech-to-text, text-to-speech and LLM orchestration into a single API call.
Key features
- Speech-to-text API for real-time transcription and batch processing
- Text-to-speech with expressive voices and latency as low as 80ms
- Unified Voice Agent API covering STT, LLM orchestration and TTS
- Audio Intelligence extracts insight from conversations
- Conversation-aware Flux models handle turn-taking and interruptions
- Deployment in the cloud or self-hosted
- Single API for speech-to-text, text-to-speech and voice agents instead of separate components
- Available in real time or batch, and in the cloud or self-hosted
- Offers separate paths for API builders, platform partners, and enterprises with custom compliance needs
- Homepage does not state pricing or plan details
- Free Flux TTS access is capped at up to 45 concurrent streaming connections in the US and 5 in the EU and AU, and runs only through September 12th
- Custom models and compliance-focused deployments require contacting sales rather than self-service
Deepgram at a glance
- Website
- deepgram.com
- Category
- AI & Machine Learning › AI Speech Transcription
- Type
- Online tool
- Pricing
- Not confirmed. Check the site
- Platforms
- Web
- Open source
- Not stated
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
Deepgram alternatives
Tools and sites you could use instead, ranked by how closely they match.
RecCloud combines speech transcription, text-to-speech, subtitle generation, video translation, and other audio and video editing tools.
Otter AI Meeting Agent supports real-time transcription, live chat, automated summaries, insights, and action items.
Speech to Note records speech, transcribes it, and organizes voice notes across Mac, Windows, mobile, and web.
Popular in AI Speech Transcription
Well-known listings from the same topic.
Deepgram FAQ
Can Deepgram be self-hosted?
Are there concurrency limits on free Flux TTS use?
What does the Voice Agent API include?
Tell us and an editor will check it.
Claim the listing and suggest updates yourself. An editor checks every claim first.










