# AI Voice Agents

> Voice agent platforms, speech-to-text, text-to-speech and realtime frameworks.

## Voice agent platforms
- [Vapi](https://voice-agents.pages.dev/tool/vapi/): Developer platform for building voice agents
- [Bland AI](https://voice-agents.pages.dev/tool/bland-ai/): AI agents that place and answer phone calls
- [Cognigy](https://voice-agents.pages.dev/tool/cognigy/): Enterprise platform for voice and chat AI agents
- [Dasha](https://voice-agents.pages.dev/tool/dasha/): Conversational AI platform for phone agents
- [Deepgram Voice Agent API](https://voice-agents.pages.dev/tool/deepgram-voice-agent-api/): Speech, language model and voice behind one API
- [ElevenLabs Agents](https://voice-agents.pages.dev/tool/elevenlabs-agents/): Conversational voice agents from ElevenLabs
- [Hume AI](https://voice-agents.pages.dev/tool/hume-ai/): Voice models that read emotional tone
- [OpenAI Realtime API](https://voice-agents.pages.dev/tool/openai-realtime-api/): Low-latency speech-in, speech-out model API
- [Parloa](https://voice-agents.pages.dev/tool/parloa/): AI agents for customer service conversations
- [PolyAI](https://voice-agents.pages.dev/tool/polyai/): Voice assistants for customer service calls
- [Retell AI](https://voice-agents.pages.dev/tool/retell-ai/): AI phone agents with a dashboard and API
- [Synthflow](https://voice-agents.pages.dev/tool/synthflow/): No-code voice AI agents for calls
- [Thoughtly](https://voice-agents.pages.dev/tool/thoughtly/): Voice and phone agents for sales and support
- [Ultravox](https://voice-agents.pages.dev/tool/ultravox/): Speech-native model and platform for voice agents
- [Voiceflow](https://voice-agents.pages.dev/tool/voiceflow/): Visual builder for chat and voice agents

## Text-to-speech
- [ElevenLabs](https://voice-agents.pages.dev/tool/elevenlabs/): Text-to-speech API and studio with many voices
- [Amazon Polly](https://voice-agents.pages.dev/tool/amazon-polly/): AWS text-to-speech service
- [Azure AI Speech Text to Speech](https://voice-agents.pages.dev/tool/azure-ai-speech-text-to-speech/): Neural voices from Microsoft Azure
- [Cartesia](https://voice-agents.pages.dev/tool/cartesia/): Low-latency speech models for realtime agents
- [Coqui TTS (Idiap fork)](https://voice-agents.pages.dev/tool/coqui-tts-idiap-fork/): Maintained fork of the Coqui TTS toolkit
- [Fish Audio](https://voice-agents.pages.dev/tool/fish-audio/): Text-to-speech and voice cloning platform
- [Google Cloud Text-to-Speech](https://voice-agents.pages.dev/tool/google-cloud-text-to-speech/): Google Cloud text-to-speech API
- [Kokoro](https://voice-agents.pages.dev/tool/kokoro/): Small open-weight text-to-speech model
- [LMNT](https://voice-agents.pages.dev/tool/lmnt/): Streaming text-to-speech and voice cloning API
- [Murf](https://voice-agents.pages.dev/tool/murf/): Text-to-speech studio for voiceovers
- [Orpheus TTS](https://voice-agents.pages.dev/tool/orpheus-tts/): Open-source speech model from Canopy Labs
- [Piper](https://voice-agents.pages.dev/tool/piper/): Fast local neural text-to-speech engine
- [Rime](https://voice-agents.pages.dev/tool/rime/): Text-to-speech tuned for conversational agents
- [Speechify](https://voice-agents.pages.dev/tool/speechify/): Reads documents and web pages aloud
- [WellSaid Labs](https://voice-agents.pages.dev/tool/wellsaid-labs/): Business voiceover with licensed actor voices

## Speech-to-text
- [Deepgram](https://voice-agents.pages.dev/tool/deepgram/): Speech-to-text and text-to-speech APIs
- [OpenAI Whisper](https://voice-agents.pages.dev/tool/openai-whisper/): Open-source multilingual speech recognition
- [Amazon Transcribe](https://voice-agents.pages.dev/tool/amazon-transcribe/): AWS speech-to-text service
- [AssemblyAI](https://voice-agents.pages.dev/tool/assemblyai/): Speech-to-text API with audio intelligence
- [faster-whisper](https://voice-agents.pages.dev/tool/faster-whisper/): Whisper reimplemented with CTranslate2
- [Gladia](https://voice-agents.pages.dev/tool/gladia/): Speech-to-text API for files and live audio
- [Google Cloud Speech-to-Text](https://voice-agents.pages.dev/tool/google-cloud-speech-to-text/): Google Cloud speech recognition API
- [NVIDIA NeMo](https://voice-agents.pages.dev/tool/nvidia-nemo/): NVIDIA framework for speech and language models
- [Rev AI](https://voice-agents.pages.dev/tool/rev-ai/): Speech-to-text API from Rev
- [Soniox](https://voice-agents.pages.dev/tool/soniox/): Speech recognition and translation API
- [Speechmatics](https://voice-agents.pages.dev/tool/speechmatics/): Speech-to-text API with many languages
- [Vosk](https://voice-agents.pages.dev/tool/vosk/): Offline speech recognition toolkit
- [whisper.cpp](https://voice-agents.pages.dev/tool/whisper-cpp/): C and C++ port of Whisper
- [WhisperX](https://voice-agents.pages.dev/tool/whisperx/): Whisper with word timestamps and diarization

## Realtime frameworks
- [LiveKit Agents](https://voice-agents.pages.dev/tool/livekit-agents/): Open-source framework for realtime voice agents
- [Agora](https://voice-agents.pages.dev/tool/agora/): Realtime voice and video SDKs with AI agents
- [Bolna](https://voice-agents.pages.dev/tool/bolna/): Open-source framework for phone voice agents
- [Daily](https://voice-agents.pages.dev/tool/daily/): WebRTC APIs and the company behind Pipecat
- [FastRTC](https://voice-agents.pages.dev/tool/fastrtc/): Python library for realtime audio apps
- [LiveKit](https://voice-agents.pages.dev/tool/livekit/): Open-source WebRTC platform with a hosted cloud
- [Moshi](https://voice-agents.pages.dev/tool/moshi/): Full-duplex speech-text model from Kyutai
- [Pipecat](https://voice-agents.pages.dev/tool/pipecat/): Python framework for voice and multimodal agents
- [RealtimeSTT](https://voice-agents.pages.dev/tool/realtimestt/): Low-latency speech-to-text Python library
- [Silero VAD](https://voice-agents.pages.dev/tool/silero-vad/): Small voice activity detection model
- [TEN Framework](https://voice-agents.pages.dev/tool/ten-framework/): Open-source framework for conversational voice AI
- [Vocode](https://voice-agents.pages.dev/tool/vocode/): Library for voice-based LLM agents

## Telephony
- [Twilio](https://voice-agents.pages.dev/tool/twilio/): Cloud communications APIs for voice and SMS
- [Amazon Connect](https://voice-agents.pages.dev/tool/amazon-connect/): AWS cloud contact center
- [Asterisk](https://voice-agents.pages.dev/tool/asterisk/): Open-source PBX and telephony toolkit
- [Bandwidth](https://voice-agents.pages.dev/tool/bandwidth/): Voice APIs on a US carrier network
- [FreeSWITCH](https://voice-agents.pages.dev/tool/freeswitch/): Open-source telephony platform and media server
- [Jambonz](https://voice-agents.pages.dev/tool/jambonz/): Open-source voice gateway for voice apps and agents
- [Plivo](https://voice-agents.pages.dev/tool/plivo/): Voice and SMS APIs with SIP trunking
- [SignalWire](https://voice-agents.pages.dev/tool/signalwire/): Programmable voice built around FreeSWITCH
- [Sinch](https://voice-agents.pages.dev/tool/sinch/): Cloud communications APIs for voice and SMS
- [Telnyx](https://voice-agents.pages.dev/tool/telnyx/): Voice, SMS and SIP trunking on a private network
- [Vonage](https://voice-agents.pages.dev/tool/vonage/): Communications APIs for voice and messaging

## Voice cloning
- [Applio](https://voice-agents.pages.dev/tool/applio/): Voice conversion tool built on RVC
- [Chatterbox](https://voice-agents.pages.dev/tool/chatterbox/): Open-source TTS from Resemble AI
- [Descript](https://voice-agents.pages.dev/tool/descript/): Audio and video editor with voice cloning
- [F5-TTS](https://voice-agents.pages.dev/tool/f5-tts/): Zero-shot open-source text-to-speech model
- [Fish Speech](https://voice-agents.pages.dev/tool/fish-speech/): Open-source TTS and voice cloning models
- [GPT-SoVITS](https://voice-agents.pages.dev/tool/gpt-sovits/): Few-shot voice cloning and text-to-speech
- [OpenVoice](https://voice-agents.pages.dev/tool/openvoice/): Open-source voice cloning from MyShell and MIT
- [Resemble AI](https://voice-agents.pages.dev/tool/resemble-ai/): Voice cloning, text-to-speech and detection
- [Respeecher](https://voice-agents.pages.dev/tool/respeecher/): Speech-to-speech voice conversion for media
- [RVC WebUI](https://voice-agents.pages.dev/tool/rvc-webui/): Open-source voice conversion from short samples
- [Tortoise TTS](https://voice-agents.pages.dev/tool/tortoise-tts/): Multi-voice TTS that clones from short clips