whereismyai
Kokoro-FastAPI
Kokoro-FastAPI is a Dockerized FastAPI wrapper for the Kokoro-82M text-to-speech model supporting multi-speaker generation.
Kokoro-FastAPI provides a Dockerized FastAPI wrapper for the Kokoro-82M text-to-speech model. It generates high quality speech and supports English, Spanish, French, Hindi, Italian, Japanese, Brazilian Portuguese, and Mandarin Chinese. Users can generate custom voicepacks, mix voices with weighted combinations, and use inline multi-speaker dialogue tags. It includes an optional integrated WebUI, streaming support, and multiple audio output formats such as mp3, wav, opus, flac, aac, and pcm. The software runs across CPU, NVIDIA GPU, AMD GPU, and Apple Silicon platforms.
Kokoro-FastAPI at a glance
- Best for: Software engineer
- Runs on: Web, Linux, macOS, Windows, API, self-hosted, open source
- Pricing: Free
- Released: December 2024
- Category: AI audio tool
- Website: github.com/remsky/Kokoro-FastAPI
Key features
- OpenAI-compatible speech endpoint
- Multi-language support
- Custom voicepack generation
- Optional integrated WebUI
- Inline multi-speaker generation
- Voice mixing and aliasing
- Timestamped caption generation
- Phoneme endpoints
Use it for
- Generating audiobooks and text reading
- Running text-to-speech for home assistants
- Creating multi-speaker voice dialogue
- Synthesizing speech via API
Alternatives to Kokoro-FastAPI
- kokoro-onnx — Runs local TTS inference with efficient ONNX runtime performance.
- AssemblyAI — Industry-leading speech models deliver high accuracy and low latency for voice applications.
- Speaches — It acts as an Ollama equivalent for running local TTS and STT models.
- Pipecat — Builds real-time voice and multimodal agents with frame-level control.
- sherpa-onnx — Runs complex audio AI tasks offline on local devices and embedded hardware.
- audio.cpp — Runs modern audio models locally with high-performance, native C++ execution.
- Piper — Runs locally and offers fast neural text-to-speech synthesis.
- Whisper ASR Webservice — Provides a REST API for multiple ASR engines including WhisperX and Faster Whisper.
- faster-whisper — Transcribes audio faster with lower memory usage than standard implementations.
- FireRedAudio — A unified model handling understanding and generation with decoupled continuous representations.
- Speech-to-Speech — Fully modular, swappable components with local or hosted execution options.
- FireRedTTS3 — It offers zero-shot voice cloning across 24 languages and 21 Chinese dialects.
All Kokoro-FastAPI alternatives