From 630d519b326542e088ca48b9034b3fd400a6b568 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?V=C3=A1clav=20Volhejn?= Date: Mon, 19 Jan 2026 10:49:03 +0100 Subject: [PATCH] Doc fixes --- README.md | 6 +++--- docs/serve.md | 4 ++-- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/README.md b/README.md index a7b5e12..18fba43 100644 --- a/README.md +++ b/README.md @@ -7,7 +7,7 @@ Forget about the hassle of using GPUs and web APIs serving TTS models. With Kyut Supports Python 3.10, 3.11, 3.12, 3.13 and 3.14. Requires PyTorch 2.5+. Does not require the gpu version of PyTorch. -[πŸ”Š Demo](https://kyutai.org/tts) | +[πŸ”Š Demo](https://kyutai.org/pocket-tts) | [πŸ±β€πŸ’»GitHub Repository](https://github.com/kyutai-labs/pocket-tts) | [πŸ€— Hugging Face Model Card](https://huggingface.co/kyutai/pocket-tts) | [πŸ“„ Paper](https://arxiv.org/abs/2509.06926) | @@ -28,7 +28,7 @@ Supports Python 3.10, 3.11, 3.12, 3.13 and 3.14. Requires PyTorch 2.5+. Does not ## Trying it from the website, without installing anything -Navigate to the [Kyutai website](https://kyutai.org/tts) to try it out directly in your browser. You can input text, select different voices, and generate speech without any installation. +Navigate to the [Kyutai website](https://kyutai.org/pocket-tts) to try it out directly in your browser. You can input text, select different voices, and generate speech without any installation. ## Trying it with the CLI @@ -122,7 +122,7 @@ You can find development instructions in the [CONTRIBUTING.md](https://github.co ## Alternative implementations -- [babybirdprd/pocket-tts](https://github.com/babybirdprd/pocket-tts) - Candle version (Rust) with WASM and PyO3 bindings. +- [babybirdprd/pocket-tts](https://github.com/babybirdprd/pocket-tts) - Candle version (Rust) with WebAssembly and PyO3 bindings. Can run in the browser! ## Projects using pocket-tts diff --git a/docs/serve.md b/docs/serve.md index 7490ccd..72c999f 100644 --- a/docs/serve.md +++ b/docs/serve.md @@ -35,10 +35,10 @@ pocket-tts serve --host "localhost" --port 8080 ```bash # Use different voice -pocket-tts serve --default-voice "hf://kyutai/tts-voices/jessica-jian/casual.wav" +pocket-tts serve --voice "hf://kyutai/tts-voices/jessica-jian/casual.wav" # Use local voice file -pocket-tts serve --default-voice "./my_voice.wav" +pocket-tts serve --voice "./my_voice.wav" ``` ## Web Interface