S

Voice Agent API

API service

by Speechmatics

Speechmatics' voice agent offering provides a real-time conversational speech API - including the Flow WebSocket endpoint that chains speech-to-text, an LLM, text-to-speech and function calling - plus a Python Voice SDK for turn detection and speaker management, and integrations with Vapi, LiveKit and Pipecat.

Find alternatives to Voice Agent API

No separate per-conversation rate is published; voice agent usage is billed through the speech-to-text and text-to-speech rate cards. The pricing page does publish a distinct quota line, 'Voice Agent conversation concurrency': 3 conversations (Free), 6 (Pro), Unlimited (Enterprise). Free API key with no card required, so the floor is 0.

What it does

• Voice agent
• Speech to text
• Text to speech

Sources

Pricing

Pricing page · 5 Sep 2026

'Voice Agent conversation concurrency' row: 3 / 6 / Unlimited across Free, Pro, Enterprise; no dedicated voice-agent rate. Floor: Free plan carries 3 voice agent conversations and needs no credit card. Floor $0.

Description

Official documentation · 5 Sep 2026

H1 'Experience Voice Agents built with Speechmatics'; page and footer name it 'Voice Agent API', cites speaker locking, dynamic Custom Dictionary, SDKs in Python/React/JavaScript, and Vapi/LiveKit/Pipecat integrations.

Sold within

Live re-check 2026-09-15: Voice Agents has no dedicated pricing line on speechmatics.com/pricing at all — it appears only as a use-case mention under Text-to-Speech, no independently-priced standalone citation.

Deployment

Official documentation · 5 Sep 2026

Page states 'Deploy agents on-prem or use our private SaaS cloud'.

Also from Speechmatics

• Speech to Text API API service

  Speechmatics' automatic speech recognition API transcribes audio into text in 55+ languages in either real-time streaming or batch mode, with speaker diarization, custom dictionary, translation and summarization options.

• Text to Speech API service

  Speechmatics' text-to-speech API generates streaming synthetic English speech from text with sub-150ms latency using four named voices (Sarah, Theo, Megan, Jack), aimed at real-time voice agent use.

• On-Device Speech to Text Developer tool

  A locally-executing speech-to-text engine for Mac and Windows laptops that runs on about one CPU core plus the device's neural engine or GPU and roughly 800MB of memory, sending no audio over a network and claiming accuracy within 5% of the cloud API.

• Translation API service

  Translates a transcript into other languages in the same API call that produces it, for files or live audio. It is a feature switched on inside a Speech to Text request rather than a separate product; the docs file it under Speech to Text and return the translations alongside the transcript.

• Summarization API service

  Generates a short summary of an audio file in the same API call that transcribes it, as paragraphs or bullets. It is a Speech Intelligence feature enabled by adding a config block to a batch Speech to Text job, not a product bought on its own.

Open Speechmatics in the directory

Something wrong here? Send a correction — quote this product id: speechmatics-voice-agent-api.