From 7573f6defb2bfd9fdbd10877d3a8e99eb718dfd9 Mon Sep 17 00:00:00 2001 From: Seth Falco Date: Tue, 24 Jan 2023 03:51:52 +0100 Subject: [PATCH] coqui (TTS): add page (#9800) --- pages/common/tts.md | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) create mode 100644 pages/common/tts.md diff --git a/pages/common/tts.md b/pages/common/tts.md new file mode 100644 index 0000000000..b52e4f4a0d --- /dev/null +++ b/pages/common/tts.md @@ -0,0 +1,28 @@ +# tts + +> Synthesize speech on the command line. +> More information: . + +- Run text-to-speech with the default models, writing the output to "tts_output.wav": + +`tts --text "{{text}}"` + +- List provided models: + +`tts --list_models` + +- Query info for a model by idx: + +`tts --model_info_by_idx {{model_type/model_query_idx}}` + +- Query info for a model by name: + +`tts --model_info_by_name {{model_type/language/dataset/model_name}}` + +- Run a text-to-speech model with its default vocoder model: + +`tts --text "{{text}}" --model_name {{model_type/language/dataset/model_name}}` + +- Run your own text-to-speech model (using the Griffin-Lim vocoder): + +`tts --text "{{text}}" --model_path {{path/to/model.pth}} --config_path {{path/to/config.json}} --out_path {{path/to/file.wav}}`