The strongest open-source alternatives to Retell AI for building AI agents — voice, speech & video ranked by GitHub traction, each with a head-to-head.
Short answer: the closest alternative to Retell AI is AssemblyAI (★ 0), the most-starred voice, speech & video; Cartesia and D-ID are also strong.
Retell AI (★ 0) is Voice-agent API for AI phone calls — build, test, and deploy production call agents with usage-based per-minute pricing. If it is not the right fit, these 18 voice, speech & video cover the same ground — AssemblyAI is the most-starred option below. Or browse the best voice, speech & video and Retell AI's own page.
Speech-to-text and audio-intelligence API — transcription, diarization, summarization, and LLM-over-audio (LeMUR). Best for agent builders.
Sonic — ultra-low-latency (~90ms), emotive real-time text-to-speech and voice cloning for live voice agents. Best for agent builders.
Talking-avatar video API — turn a photo + text/audio into a lip-synced presenter, with real-time WebRTC streaming agents. Best for agent builders.
Fast, accurate speech-to-text, text-to-speech, and voice-agent APIs built for real-time and batch at scale. Best for agent builders.
Ultra-realistic text-to-speech, voice cloning, dubbing, and voice-agent APIs for developers and creators. Best for agent builders.
OpenAudio (S1/S2) text-to-speech and voice cloning — open models plus a hosted pay-as-you-go API. Best for agent builders.
Audio-infrastructure API for voice products — async and real-time speech-to-text with diarization and translation. Best for agent builders.
Programmatic AI avatar video generation and video translation/dubbing with lip-sync, via a REST API. Best for agent builders.
Empathic Voice Interface (EVI) and Octave TTS — emotionally intelligent, context-aware expressive speech. Best for agent builders.
Low-latency (150–200ms) multilingual text-to-speech with studio-quality voices and instant cloning. Best for agent builders.
Generative text-to-speech API with 900+ voices, instant voice cloning, and low-latency streaming for conversational AI. Best for agent builders.
Voice cloning and generative speech API, plus deepfake detection and audio watermarking, billed per second. Best for agent builders.
Enterprise TTS with 200+ realistic voices, sub-200ms latency, and linguistically-aware markup for voice agents. Best for agent builders.
High-accuracy speech-to-text across 55+ languages, plus real-time transcription and the Flow voice-agent API. Best for agent builders.
Studio-grade AI lip-sync and visual dubbing API — retime any video's mouth to new audio in any language. Best for agent builders.
Studio-grade AI avatar video generation API — script-to-video with 200+ avatars, translation, and templates. Best for agent builders.
Conversational Video Interface (CVI) and Phoenix replica API — real-time, face-to-face AI video agents ('digital twins'). Best for agent builders.
Developer-first platform to build, test, and deploy real-time voice AI agents with pluggable STT/LLM/TTS and telephony. Best for agent builders.
AssemblyAI (★ 0) is the most-starred voice, speech & video alternative to Retell AI. Speech-to-text and audio-intelligence API — transcription, diarization, summarization, and LLM-over-audio (LeMUR).
The strongest voice, speech & video alternatives to Retell AI are AssemblyAI, Cartesia, D-ID, Deepgram and more — each with a head-to-head comparison.
Yes — the alternatives listed are open source and free to self-host; you bring your own model keys.
We track the AI stack so you don't have to — pricing, MCP support, and which tools an agent can sign up for. Free.