AI Voice Agents

Deepgram

Speech-to-text and text-to-speech APIs

Deepgram provides speech-to-text and text-to-speech APIs for batch and realtime audio. Its Nova models are built for low latency and are used in call transcription and voice agents.

sttstreamingapicall-transcription

More in Speech-to-text

Featured

OpenAI Whisper

Speech-to-text

Open-source multilingual speech recognition

Open sourcesttwhisper

Amazon Transcribe

Speech-to-text

AWS speech-to-text service

Paidsttaws

AssemblyAI

Speech-to-text

Speech-to-text API with audio intelligence

Freemiumsttdiarization

faster-whisper

Speech-to-text

Whisper reimplemented with CTranslate2

Open sourcesttwhisper

Gladia

Speech-to-text

Speech-to-text API for files and live audio

Freemiumsttstreaming

Google Cloud Speech-to-Text

Speech-to-text

Google Cloud speech recognition API

Freemiumsttgoogle-cloud