Cartesia Voice Agent stack

by Cartesia

Cartesia's Sonic TTS plus partner ASR/LLM for low-latency voice agents.

TL;DR

Cartesia's Sonic TTS plus partner ASR/LLM for low-latency voice agents.

Best for developers prioritizing sub-100ms TTS first-byte latency in agents. Pricing: see vendor pricing.

Category
Transcription APIs
License
—
Stars
—
Last push
—
Pricing
see vendor pricing
Platforms
Cloud, API

What it is

Cartesia ships the Sonic family of state-space TTS models claimed to deliver sub-100ms first-audio latency. Combined with Deepgram or AssemblyAI ASR plus an LLM, Cartesia powers a popular low-latency voice-agent stack widely deployed in Pipecat, LiveKit Agents, and Vapi configurations.

Best for: Developers prioritizing sub-100ms TTS first-byte latency in agents.
Watch out for: TTS-led; needs paired ASR and LLM providers.

Features

Speaker diarizationNo
Word-level timestampsNo
Streaming / real-timeNo
Languages supportedNone
HIPAA eligibleNo

Cartesia Voice Agent stack vs Whipscribe

FeatureCartesia Voice Agent stackWhipscribe
CategoryTranscription APIsTranscription APIs
Pricingsee vendor pricingfree beta
Speaker diarization—Yes
Word timestamps—Yes
Streaming—No
Languages—99
PlatformsCloud, APIWeb, API, MCP

Alternatives to Cartesia Voice Agent stack

OpenAI Whisper API
OpenAI

Hosted Whisper large-v3 from OpenAI — $0.006 per minute.

$0.006/min
AssemblyAI
AssemblyAI

Universal-2 model + diarization, PII redaction, topic detection, summarization.

from $0.37/hr
Deepgram
Deepgram

Nova-2 model, excellent streaming, strong at conversational audio.

from $0.0043/min

Whipscribe is a managed faster-whisper + whisperX service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.