> ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. --- title: "Voice & Real-Time Agents" url: https://daily.dev/agentic-ai-hub/voice-real-time-agents/ description: "Real-time voice agents = STT (speech-to-text) β†’ LLM β†’ TTS (text-to-speech) stitched into a low-latency loop (or, increasingly, a single speech-to-speech model)." lastUpdated: "2026-07-22" --- Real-time voice agents = **STT (speech-to-text) β†’ LLM β†’ TTS (text-to-speech)** stitched into a low-latency loop (or, increasingly, a single speech-to-speech model). The "platform" layer (Vapi/Retell/Bland) handles telephony, turn-taking, and orchestration; the "infra" layer (LiveKit/Pipecat) gives you the transport/pipeline to build your own; and the "model" layer (ElevenLabs/Deepgram/Cartesia + realtime APIs) supplies the ears and voice. All πŸ”„. Pricing here is per-minute and shifts often. ## Platforms (build a phone/voice agent fast) | Platform | Best at | Watch out | Price | | :---- | :---- | :---- | :---- | | [Vapi](https://vapi.ai) | Fast time-to-production with pluggable STT/LLM/TTS, function calling, and telephony; big ecosystem | Per-minute cost stacks (platform + each model + telephony), so model your unit economics | Usage-based, ~$0.05+/min plus provider costs πŸ”„ | | [Retell AI](https://www.retellai.com) | Natural turn-taking and call reliability for support/sales | None | Usage-based per minute πŸ”„ | | [Bland AI](https://www.bland.ai) | High-volume outbound/inbound calling with an all-in-one stack | More closed than Vapi or Retell | Usage-based πŸ”„ | *Also:* [**Synthflow**](https://synthflow.ai), [**Vocode**](https://www.vocode.dev) (open source). ## Infrastructure (build your own pipeline) | Tool | Best at | Key fact | | :---- | :---- | :---- | | [LiveKit](https://livekit.io) | Scalable real-time audio/video transport and building custom voice agents (self-host or cloud); the transport backbone many voice apps and some labs' voice features run on | Open-source WebRTC platform + an **Agents** framework; LiveKit Cloud is usage-priced | | [Pipecat](https://www.pipecat.ai) | Composing the STTβ†’LLMβ†’TTS pipeline with full control and vendor-swappable components | Open-source Python framework (BSD), originated at Daily | | [Ultravox](https://www.ultravox.ai) | Lower-latency, more natural voice by feeding audio straight into an LLM-derived model | Open-weight **speech-to-speech** that skips separate STT; open weights + hosted API, per-minute πŸ”„ | ## Voices & ears (TTS / STT / realtime models) | Tool | Best at | Watch out | Price | | :---- | :---- | :---- | :---- | | [ElevenLabs](https://elevenlabs.io) | Natural, expressive **TTS**, voice cloning, dubbing, and a full **Agents** platform; broad language coverage | Premium pricing; voice-cloning consent/ethics matter | Free tier + paid from ~$5/mo (character-metered) πŸ”„ | | [Deepgram](https://deepgram.com) | Fast, accurate, cheap streaming **STT** (and now TTS) at scale (Nova-series) | None | Usage-based per minute/hour; free credits to start πŸ”„ | | [Cartesia](https://cartesia.ai) | The fastest realtime **TTS** (Sonic, state-space models) with tiny time-to-first-audio | None | Usage-based, free tier πŸ”„ | *Realtime APIs:* [**OpenAI Realtime API**](https://platform.openai.com/docs/guides/realtime) (speech-to-speech via GPT-4o-realtime/successors), [**Google Gemini Live API**](https://ai.google.dev/gemini-api/docs/live), [**AssemblyAI**](https://www.assemblyai.com) (STT with speech understanding). **Latency budget rule:** conversational agents feel natural under ~800ms round-trip. Speech-to-speech models (Ultravox, OpenAI Realtime) cut the STT/TTS hops. Classic pipelines win on component choice and cost control.