Tortoise TTS

Spec sheet

Purpose

Tortoise is a text-to-speech program focused on multi-voice capability and realistic prosody and intonation.Read 12 Oct 2026 · github.com

Platforms

windows,macos,api,self_hostedRead 20 Sep 2026 · github.com

License

Tortoise TTS is licensed under Apache 2.0.Read 12 Oct 2026 · github.com

Maker

The author identifies himself as James Betker and says his employer was not involved in the project’s development.Read 12 Oct 2026 · github.com

API access

YesRead 20 Sep 2026 · github.com

Custom voices

Users can add a voice by providing at least three roughly 10-second WAV clips at 22,050 Hz.Read 12 Oct 2026 · github.com

Dependencies

The project acknowledges Hugging Face for the GPT model and generation API and for hosting model weights.Read 12 Oct 2026 · github.com

Hardware

The README says local use requires an NVIDIA GPU and describes a separate Apple Silicon setup for macOS 13 or later with M1 or M2 chips.Read 12 Oct 2026 · github.com

Hosted demo

A live demo is hosted on Hugging Face Spaces, and the README says CPU-only Spaces do not work for it.Read 12 Oct 2026 · github.com

Inference

The repository contains the code needed to run Tortoise TTS in inference mode.Read 12 Oct 2026 · github.com

Long text

The read and read_fast scripts split text files into speech clips and can combine the clips into one file.Read 12 Oct 2026 · github.com

Programmatic use

The Python API accepts reference audio and generates speech using a selected preset.Read 12 Oct 2026 · github.com

Streaming

The repository includes a socket streaming server that listens on port 5000.Read 12 Oct 2026 · github.com

Voice cloning

YesRead 20 Sep 2026 · github.com

Voice references

The model uses speaker reference clips to guide voice qualities such as pitch, tone, and speaking speed.Read 12 Oct 2026 · github.com

Plans and prices

Every Tortoise TTS plan and price →

Where Specifiction places it

• Text-to-speech tools#101 of 2328.0
• Text-to-Speech Software#136 of 2227.8