Ink is Cartesia's streaming speech-to-text model for voice-agent transcription with native turn detection.
Ink converts streaming audio into text transcripts for production voice agents, handling telephony, accents, background noise, and structured data like phone numbers and dates. It signals turn start, turn end, and eager end natively, so teams need no separate voice-activity detector.
The current version Ink-2 supports English, Spanish, French, Hindi, and Japanese and runs in the cloud, on-premises including air-gapped environments, customer VPC, or via OEM licensing. It serves healthcare, financial services, insurance, and government teams needing HIPAA compliance, SOC 2 Type 2, and zero-data-retention terms.
Deepgram
Deepgram Speech-to-Text API
deepgram.com
AssemblyAI
Realtime Speech-to-Text
assemblyai.com
ElevenLabs
Scribe
elevenlabs.io
| Attribute | Ink | Deepgram Speech-to-Text API | Realtime Speech-to-Text | Scribe | |
|---|---|---|---|---|---|
| Provider | | | | | |
| Founded | 2023 | 2015 | 2017 | 2022 | |
| Sells To | Enterprises | Enterprise, Small Business | — | B2B, B2C, Enterprises | |
| Pricing Model | Recurring, Software | Recurring, Software, Usage-based | — | B2B Subscription, Recurring, Usage-based | |
| Ownership | Private | Venture-backed | Venture-backed | Private, Venture-backed |
Provider
Founded 2023
Sells To Enterprises
Pricing Model Recurring, Software
Ownership Private
Provider
Founded 2015
Sells To Enterprise, Small Business
Pricing Model Recurring, Software, Usage-based
Ownership Venture-backed
Provider
Founded 2017
Sells To —
Pricing Model —
Ownership Venture-backed
Provider
Founded 2022
Sells To B2B, B2C, Enterprises
Pricing Model B2B Subscription, Recurring, Usage-based
Ownership Private, Venture-backed
Agent STT is a real-time speech-to-text API package built for AI voice agent workloads.
AssemblyAI's Speech-to-Text API transcribes audio in streaming and pre-recorded modes with speaker diarization.
Unified web API exposing multilingual AI capabilities including machine translation, sentiment analysis, intent detection, and speech transcription.
Developer API platform for production-ready speech, transcription, music, agents, and audio generation.
Gemini Live API enables real-time voice and vision interactions through streaming conversational models.
Besimple AI's conversational audio training-data offering.
Speechmatics' Speech-to-Text API is a multilingual automatic speech recognition service offered in real-time and batch modes with speaker diarization.
Offline-capable voice-to-text software that types polished text into any app.
Voice-to-text software that turns speech into formatted writing across apps.
Voice AI agent platform for building, scaling, and iterating AI-powered phone agents on carrier-grade infrastructure.
Developer platform providing real-time and batch APIs for speech-to-text, text-to-speech, and voice agents.
Agent STT is a real-time speech-to-text API package built for AI voice agent workloads.
AssemblyAI's Speech-to-Text API transcribes audio in streaming and pre-recorded modes with speaker diarization.
Unified web API exposing multilingual AI capabilities including machine translation, sentiment analysis, intent detection, and speech transcription.
Inscribe runs an agentic document fraud detection platform for financial services lenders and risk teams.
Developer API platform for production-ready speech, transcription, music, agents, and audio generation.
Gemini Live API enables real-time voice and vision interactions through streaming conversational models.
Besimple AI's conversational audio training-data offering.
Speechmatics' Speech-to-Text API is a multilingual automatic speech recognition service offered in real-time and batch modes with speaker diarization.
Offline-capable voice-to-text software that types polished text into any app.
Voice-to-text software that turns speech into formatted writing across apps.
Voice AI agent platform for building, scaling, and iterating AI-powered phone agents on carrier-grade infrastructure.
Developer platform providing real-time and batch APIs for speech-to-text, text-to-speech, and voice agents.
