🎙️Voice AgentsCreate AI agents with custom personalities, knowledge bases, and tools. Deploy to phone calls, WebSocket, or WhatsApp.
🎬Video Generation & AvatarsText-to-video, talking-head avatars, lipsync, dubbing — all async. 17 providers from Sora to open-source.
🔊12 TTS / 10 STT ProvidersCartesia, ElevenLabs, Deepgram, Fish Audio, Whisper, Groq. Swap providers per request. BYOK skips metering.
🧬Voice CloningClone any voice from a 30-second sample. Use the same voice across TTS, video avatars, and dub.
🧠Frontier LLM ModelsGPT-5, Claude Opus 4.7, Llama 4 on Groq LPU, GLM-4. Pick a model per turn or rotate for resilience.
📚Knowledge (RAG)Ingest documents, transcripts, and audio into vector collections. Agents auto-retrieve per turn.
⚡Real-Time SessionsSub-second voice loop. Twilio integration, WebSocket streaming, barge-in, interruption handling.
💳BYOK or Free Tier2,500 free credits/month. Pay-as-you-go from $29/mo. BYOK skips our metering entirely.