
Kokori converts text to speech on macOS using a local API server and desktop app, providing high-quality voices, speed control, and menubar-based playback management.
Kokori is a macOS text-to-speech (TTS) solution designed for users who need high-quality, controllable voice output directly on their desktop. It combines a native menubar app with a local API server, allowing both manual use and programmatic integration into existing workflows. The primary purpose of Kokori is to turn written content into natural-sounding speech while keeping processing local, responsive, and under the userβs control.
The tool offers a range of high-quality voices with adjustable speaking rates, enabling users to fine-tune output for clarity, pacing, or specific listening preferences. Its menubar integration provides quick access to core functions, so users can convert text to audio without interrupting their current tasks. The built-in local API server makes it straightforward for developers to connect scripts, automation tools, or custom apps to Kokori for automated TTS tasks. Because it runs locally, Kokori can offer lower latency and improved privacy compared to cloud-only services.
Please sign in to comment
π¬ No comments yet
Be the first to share your thoughts!
Explore 306+ top alternatives to Kokori

ElevenLabs is an AI platform for generating, editing, and managing natural-sounding multilingual speech and custom voice clones via web tools and developer APIs.

KrispCall is a virtual cloud phone system with AI for making and receiving VoIP calls and SMS to local and international numbers from a single app.

Dearflow is an AI email assistant that organizes incoming messages by topic and generates reply drafts that match the userβs writing style and tone.

Speak4me is a text-to-speech tool that converts documents, PDFs, and web pages into audio so users can listen to written content on any device.

Astica provides AI libraries for computer vision, speech generation, and speech-to-text dictation, enabling developers to add automated perception and interaction features to their applications.
Text to Speech is a web-based API that converts written text into natural-sounding speech and provides speech recognition capabilities for applications and services.

Thoughtly is a no-code platform that enables businesses to design, deploy, and manage AI voice agents for handling customer phone calls and contact center interactions.

Quickads is an AI-powered platform that generates image and video advertisements in seconds, enabling rapid creation and iteration of ad creatives for digital marketing campaigns.

Cordless IO is a platform for building and deploying AI voice agents that handle customer support calls, automate conversations, and integrate with existing contact center systems.