Parler TTS
Contrary to other TTS models, Parler-TTS is a fully open-source release. All of the datasets, pre-processing, training code, and weights are released publicly under a permissive license, enabling the community to build on our work and develop their own powerful TTS models.\nIt consists in:
\n- \n
- The Parler-TTS library for using and training high-quality TTS models. \n
- The Data-Speech repository, for annotating speech characteristics in a large-scale setting. \n
- This organization, that contains the released datasets and weights. \n
🚨 Two new checkpoints, Parler-TTS Mini v1.1 and Large v1, are out! 🚨\nTrained on 45k hours of narrated audio, they're better and faster than previous versions, and introduce speaker consistency across generations.\nTry them out here 🤗!
\n","classNames":"hf-sanitized hf-sanitized-8nzIaO1xb5tlzRHHl88SA"},"users":[{"_id":"62611fcabbcbd1c34f1615f6","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62611fcabbcbd1c34f1615f6/tXx0cbsnQM03EinbKMY0x.jpeg","isPro":false,"fullname":"Yoach Lacombe","user":"ylacombe","type":"user"},{"_id":"660bc459d81d6112496f30f8","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/660bc459d81d6112496f30f8/jMrpAckFyg-_iHMI7sn2h.jpeg","isPro":false,"fullname":"Eustache Le Bihan","user":"eustlb","type":"user"},{"_id":"626a9bfa03e2e2796f24ca11","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1654278567459-626a9bfa03e2e2796f24ca11.jpeg","isPro":true,"fullname":"Freddy Boulton","user":"freddyaboulton","type":"user"},{"_id":"654bcb6fae75d15300d48205","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/654bcb6fae75d15300d48205/T4L1RZUgCZgdik4ZhEWCq.jpeg","isPro":true,"fullname":"Steven Zheng","user":"Steveeeeeeen","type":"user"}],"userCount":4,"collections":[{"slug":"parler-tts/parler-tts-fully-open-source-high-quality-tts-66164ad285ba03e8ffde214c","title":"Parler-TTS: fully open-source high-quality TTS","description":" If you want to find out more about how these models were trained and even fine-tune them yourself, check-out the Parler-TTS repository on GitHub.","gating":false,"lastUpdated":"2024-12-02T17:08:58.593Z","owner":{"_id":"65d32204dd8292fdc69a11d9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62611fcabbcbd1c34f1615f6/derNQFLKSTg-Y-jMUCKtD.png","fullname":"Parler TTS","name":"parler-tts","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":331,"isUserFollowing":false},"items":[{"_id":"66164b0251c9b8e0e0275d4c","position":0,"type":"space","author":"parler-tts","authorData":{"_id":"65d32204dd8292fdc69a11d9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62611fcabbcbd1c34f1615f6/derNQFLKSTg-Y-jMUCKtD.png","fullname":"Parler TTS","name":"parler-tts","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":331,"isUserFollowing":false},"colorFrom":"blue","colorTo":"pink","createdAt":"2024-04-09T10:59:03.000Z","emoji":"🥖","id":"parler-tts/parler_tts","lastModified":"2025-11-18T12:10:26.000Z","likes":844,"pinned":true,"private":false,"sdk":"gradio","repoType":"space","runtime":{"stage":"RUNNING","hardware":{"current":"zero-a10g","requested":"zero-a10g"},"storage":null,"gcTimeout":172800,"replicas":{"current":1,"requested":1},"devMode":false,"domains":[{"domain":"parler-tts-parler-tts.hf.space","stage":"READY"}],"sha":"e19b27c8b09c2ba343d3c82b2f6af7ddfff7ee8c"},"shortDescription":"High-fidelity Text-To-Speech","title":"Parler-TTS","isLikedByUser":false,"ai_short_description":"Generate natural-sounding speech from text with voice control","ai_category":"Speech Synthesis","trendingScore":0,"tags":["gradio","region:us"],"featured":true},{"_id":"674de93c6663f2a6f5ac3cdf","position":1,"type":"model","note":{"html":"Parler-TTS Mini v1.1 is a 938M parameters Parler checkpoint, trained on 45K hours of audio data. The only change with v1 is the use of a better prompt tokenizer. This tokenizer has a larger vocabulary and handles byte fallback, which simplifies multilingual training.","text":"Parler-TTS Mini v1.1 is a 938M parameters Parler checkpoint, trained on 45K hours of audio data. The only change with v1 is the use of a better prompt tokenizer. This tokenizer has a larger vocabulary and handles byte fallback, which simplifies multilingual training."},"author":"parler-tts","authorData":{"_id":"65d32204dd8292fdc69a11d9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62611fcabbcbd1c34f1615f6/derNQFLKSTg-Y-jMUCKtD.png","fullname":"Parler TTS","name":"parler-tts","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":331,"isUserFollowing":false},"downloads":1067,"gated":false,"id":"parler-tts/parler-tts-mini-v1.1","availableInferenceProviders":[],"lastModified":"2024-10-30T15:54:24.000Z","likes":27,"pipeline_tag":"text-to-speech","private":false,"repoType":"model","isLikedByUser":false,"numParameters":937803241},{"_id":"66b4e9c18de19c0bb31ff72a","position":2,"type":"model","note":{"html":"Parler-TTS Large is a 2.2B-parameters Parler checkpoint, trained on 45K hours of audio data.","text":"Parler-TTS Large is a 2.2B-parameters Parler checkpoint, trained on 45K hours of audio data."},"author":"parler-tts","authorData":{"_id":"65d32204dd8292fdc69a11d9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62611fcabbcbd1c34f1615f6/derNQFLKSTg-Y-jMUCKtD.png","fullname":"Parler TTS","name":"parler-tts","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":331,"isUserFollowing":false},"downloads":11018,"gated":false,"id":"parler-tts/parler-tts-large-v1","availableInferenceProviders":[],"lastModified":"2024-11-22T16:17:20.000Z","likes":272,"pipeline_tag":"text-to-speech","private":false,"repoType":"model","isLikedByUser":false,"numParameters":2333013362},{"_id":"66b4e9125086002e2d9529d5","position":3,"type":"model","note":{"html":"Parler-TTS Mini is a 880M parameters Parler checkpoint, trained on 45K hours of audio data.","text":"Parler-TTS Mini is a 880M parameters Parler checkpoint, trained on 45K hours of audio data."},"author":"parler-tts","authorData":{"_id":"65d32204dd8292fdc69a11d9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62611fcabbcbd1c34f1615f6/derNQFLKSTg-Y-jMUCKtD.png","fullname":"Parler TTS","name":"parler-tts","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":331,"isUserFollowing":false},"downloads":16043,"gated":false,"id":"parler-tts/parler-tts-mini-v1","availableInferenceProviders":[],"lastModified":"2024-11-25T11:26:20.000Z","likes":152,"pipeline_tag":"text-to-speech","private":false,"repoType":"model","isLikedByUser":false,"numParameters":877842290}],"position":0,"theme":"indigo","private":false,"shareUrl":"https://hf.co/collections/parler-tts/parler-tts-fully-open-source-high-quality-tts","upvotes":51,"isUpvotedByUser":false},{"slug":"parler-tts/parler-tts-expresso-6644cf894e52ac200d7144d4","title":"Parler-TTS: Expresso ☕️","description":"Parler-TTS v0.1 fine-tuned on the Expresso dataset, for expressive, voice-consistent generations.","gating":false,"lastUpdated":"2024-08-07T13:16:11.561Z","owner":{"_id":"65d32204dd8292fdc69a11d9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62611fcabbcbd1c34f1615f6/derNQFLKSTg-Y-jMUCKtD.png","fullname":"Parler TTS","name":"parler-tts","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":331,"isUserFollowing":false},"items":[{"_id":"6644cfabe1e0c98fdb363649","position":0,"type":"space","author":"parler-tts","authorData":{"_id":"65d32204dd8292fdc69a11d9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62611fcabbcbd1c34f1615f6/derNQFLKSTg-Y-jMUCKtD.png","fullname":"Parler TTS","name":"parler-tts","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":331,"isUserFollowing":false},"colorFrom":"red","colorTo":"blue","createdAt":"2024-05-10T15:26:43.000Z","emoji":"⚡","id":"parler-tts/parler-tts-expresso","lastModified":"2024-05-17T11:17:01.000Z","likes":92,"pinned":false,"private":false,"sdk":"gradio","repoType":"space","runtime":{"stage":"RUNNING","hardware":{"current":"zero-a10g","requested":"zero-a10g"},"storage":null,"gcTimeout":172800,"replicas":{"current":1,"requested":1},"devMode":false,"domains":[{"domain":"parler-tts-parler-tts-expresso.hf.space","stage":"READY"}],"sha":"76a0ee2944cebbc4f5b22e0f770e3eb75e282f4d"},"title":"Parler TTS Expresso","isLikedByUser":false,"ai_short_description":"Convert text to speech with emotion","ai_category":"Speech Synthesis","trendingScore":0,"tags":["gradio","region:us"],"featured":false},{"_id":"6644cfc576c0a469f693462b","position":1,"type":"model","author":"parler-tts","authorData":{"_id":"65d32204dd8292fdc69a11d9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62611fcabbcbd1c34f1615f6/derNQFLKSTg-Y-jMUCKtD.png","fullname":"Parler TTS","name":"parler-tts","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":331,"isUserFollowing":false},"downloads":568,"gated":false,"id":"parler-tts/parler-tts-mini-expresso","availableInferenceProviders":[],"lastModified":"2024-05-21T17:17:04.000Z","likes":115,"pipeline_tag":"text-to-speech","private":false,"repoType":"model","isLikedByUser":false},{"_id":"6644cfce7b1121f492e5d04c","position":2,"type":"dataset","author":"ylacombe","downloads":1314,"gated":false,"id":"ylacombe/expresso","lastModified":"2024-04-30T16:49:14.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":11615,"libraries":["datasets","dask","mlcroissant","polars"],"formats":["parquet"],"modalities":["audio","text"]},"private":false,"repoType":"dataset","likes":79,"isLikedByUser":false,"isBenchmark":false}],"position":1,"theme":"green","private":false,"shareUrl":"https://hf.co/collections/parler-tts/parler-tts-expresso","upvotes":6,"isUpvotedByUser":false},{"slug":"parler-tts/open-source-speech-datasets-annotated-using-data-speech-661648ffa0d3d76bfa23d534","title":"Open-source speech datasets annotated using Data-Speech","description":"Open-source annotated speech datasets ranging from 1,000 hours to 45,000 hours.","gating":false,"lastUpdated":"2024-08-08T14:15:43.268Z","owner":{"_id":"65d32204dd8292fdc69a11d9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62611fcabbcbd1c34f1615f6/derNQFLKSTg-Y-jMUCKtD.png","fullname":"Parler TTS","name":"parler-tts","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":331,"isUserFollowing":false},"items":[{"_id":"66b3726e487c05514ef12501","position":0,"type":"dataset","note":{"html":"The English version of the Multilingual LibriSpeech (MLS) dataset. ","text":"The English version of the Multilingual LibriSpeech (MLS) dataset. "},"author":"parler-tts","downloads":3321,"gated":false,"id":"parler-tts/mls_eng","lastModified":"2024-04-09T14:37:17.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":10815613,"libraries":["datasets","dask","mlcroissant","polars"],"formats":["parquet"],"modalities":["audio","text"]},"private":false,"repoType":"dataset","likes":32,"isLikedByUser":false,"isBenchmark":false},{"_id":"66b3728d55d04222776a940a","position":1,"type":"dataset","note":{"html":"Filtered version of the 1K high-quality LibriTTS-R dataset.","text":"Filtered version of the 1K high-quality LibriTTS-R dataset."},"author":"parler-tts","downloads":2454,"gated":false,"id":"parler-tts/libritts_r_filtered","lastModified":"2024-08-06T16:45:54.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":358503,"libraries":["datasets","dask","mlcroissant","polars"],"formats":["parquet"],"modalities":["audio","text"]},"private":false,"repoType":"dataset","likes":21,"isLikedByUser":false,"isBenchmark":false},{"_id":"66b3728073035b43e6eaef63","position":2,"type":"dataset","note":{"html":"Annotations of English MLS above. Used for v1 training.","text":"Annotations of English MLS above. Used for v1 training."},"author":"parler-tts","downloads":182,"gated":false,"id":"parler-tts/mls-eng-speaker-descriptions","lastModified":"2024-08-08T12:55:57.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":10815613,"libraries":["datasets","dask","mlcroissant","polars"],"formats":["parquet"],"modalities":["tabular","text"]},"private":false,"repoType":"dataset","likes":11,"isLikedByUser":false,"isBenchmark":false},{"_id":"66b37286820f521297f1363c","position":3,"type":"dataset","note":{"html":" Annotations of the filtered LibriTTS-R dataset. Used for v1 training.","text":" Annotations of the filtered LibriTTS-R dataset. Used for v1 training."},"author":"parler-tts","downloads":45,"gated":false,"id":"parler-tts/libritts-r-filtered-speaker-descriptions","lastModified":"2024-08-08T12:56:46.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":358503,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["tabular","text"]},"private":false,"repoType":"dataset","likes":7,"isLikedByUser":false,"isBenchmark":false}],"position":2,"theme":"pink","private":false,"shareUrl":"https://hf.co/collections/parler-tts/open-source-speech-datasets-annotated-using-data-speech","upvotes":5,"isUpvotedByUser":false}],"datasets":[{"author":"parler-tts","downloads":9314,"gated":false,"id":"parler-tts/images","lastModified":"2024-12-03T15:13:08.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":2,"libraries":["datasets","mlcroissant"],"formats":["imagefolder"],"modalities":["image"]},"private":false,"repoType":"dataset","likes":0,"isLikedByUser":false,"isBenchmark":false},{"author":"parler-tts","downloads":45,"gated":false,"id":"parler-tts/libritts-r-filtered-speaker-descriptions","lastModified":"2024-08-08T12:56:46.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":358503,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["tabular","text"]},"private":false,"repoType":"dataset","likes":7,"isLikedByUser":false,"isBenchmark":false},{"author":"parler-tts","downloads":182,"gated":false,"id":"parler-tts/mls-eng-speaker-descriptions","lastModified":"2024-08-08T12:55:57.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":10815613,"libraries":["datasets","dask","mlcroissant","polars"],"formats":["parquet"],"modalities":["tabular","text"]},"private":false,"repoType":"dataset","likes":11,"isLikedByUser":false,"isBenchmark":false},{"author":"parler-tts","downloads":2454,"gated":false,"id":"parler-tts/libritts_r_filtered","lastModified":"2024-08-06T16:45:54.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":358503,"libraries":["datasets","dask","mlcroissant","polars"],"formats":["parquet"],"modalities":["audio","text"]},"private":false,"repoType":"dataset","likes":21,"isLikedByUser":false,"isBenchmark":false},{"author":"parler-tts","downloads":28,"gated":false,"id":"parler-tts/mls-eng-10k-tags_tagged_10k_generated","lastModified":"2024-04-10T11:45:51.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":2427623,"libraries":["datasets","dask","mlcroissant","polars"],"formats":["parquet"],"modalities":["tabular","text"]},"private":false,"repoType":"dataset","likes":17,"isLikedByUser":false,"isBenchmark":false},{"author":"parler-tts","downloads":29,"gated":false,"id":"parler-tts/libritts_r_tags_tagged_10k_generated","lastModified":"2024-04-10T11:44:51.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":364650,"libraries":["datasets","pandas","mlcroissant","polars"],"formats":["parquet"],"modalities":["tabular","text"]},"private":false,"repoType":"dataset","likes":9,"isLikedByUser":false,"isBenchmark":false},{"author":"parler-tts","downloads":904,"gated":false,"id":"parler-tts/mls_eng_10k","lastModified":"2024-04-09T14:41:38.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":2427623,"libraries":["datasets","dask","mlcroissant","polars"],"formats":["parquet"],"modalities":["audio","text"]},"private":false,"repoType":"dataset","likes":31,"isLikedByUser":false,"isBenchmark":false},{"author":"parler-tts","downloads":3321,"gated":false,"id":"parler-tts/mls_eng","lastModified":"2024-04-09T14:37:17.000Z","datasetsServerInfo":{"viewer":"viewer","numRows":10815613,"libraries":["datasets","dask","mlcroissant","polars"],"formats":["parquet"],"modalities":["audio","text"]},"private":false,"repoType":"dataset","likes":32,"isLikedByUser":false,"isBenchmark":false}],"models":[{"author":"parler-tts","authorData":{"_id":"65d32204dd8292fdc69a11d9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62611fcabbcbd1c34f1615f6/derNQFLKSTg-Y-jMUCKtD.png","fullname":"Parler TTS","name":"parler-tts","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":331,"isUserFollowing":false},"downloads":282280,"gated":false,"id":"parler-tts/parler-tts-mini-multilingual-v1.1","availableInferenceProviders":[],"lastModified":"2024-12-04T18:23:03.000Z","likes":54,"pipeline_tag":"text-to-speech","private":false,"repoType":"model","isLikedByUser":false,"numParameters":937803241},{"author":"parler-tts","authorData":{"_id":"65d32204dd8292fdc69a11d9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62611fcabbcbd1c34f1615f6/derNQFLKSTg-Y-jMUCKtD.png","fullname":"Parler TTS","name":"parler-tts","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":331,"isUserFollowing":false},"downloads":94,"gated":false,"id":"parler-tts/parler-tts-mini-multilingual","availableInferenceProviders":[],"lastModified":"2024-12-02T17:21:40.000Z","likes":27,"pipeline_tag":"text-to-speech","private":false,"repoType":"model","isLikedByUser":false,"numParameters":937803241},{"author":"parler-tts","authorData":{"_id":"65d32204dd8292fdc69a11d9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62611fcabbcbd1c34f1615f6/derNQFLKSTg-Y-jMUCKtD.png","fullname":"Parler TTS","name":"parler-tts","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":331,"isUserFollowing":false},"downloads":16043,"gated":false,"id":"parler-tts/parler-tts-mini-v1","availableInferenceProviders":[],"lastModified":"2024-11-25T11:26:20.000Z","likes":152,"pipeline_tag":"text-to-speech","private":false,"repoType":"model","isLikedByUser":false,"numParameters":877842290},{"author":"parler-tts","authorData":{"_id":"65d32204dd8292fdc69a11d9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62611fcabbcbd1c34f1615f6/derNQFLKSTg-Y-jMUCKtD.png","fullname":"Parler TTS","name":"parler-tts","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":331,"isUserFollowing":false},"downloads":11018,"gated":false,"id":"parler-tts/parler-tts-large-v1","availableInferenceProviders":[],"lastModified":"2024-11-22T16:17:20.000Z","likes":272,"pipeline_tag":"text-to-speech","private":false,"repoType":"model","isLikedByUser":false,"numParameters":2333013362},{"author":"parler-tts","authorData":{"_id":"65d32204dd8292fdc69a11d9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62611fcabbcbd1c34f1615f6/derNQFLKSTg-Y-jMUCKtD.png","fullname":"Parler TTS","name":"parler-tts","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":331,"isUserFollowing":false},"downloads":1067,"gated":false,"id":"parler-tts/parler-tts-mini-v1.1","availableInferenceProviders":[],"lastModified":"2024-10-30T15:54:24.000Z","likes":27,"pipeline_tag":"text-to-speech","private":false,"repoType":"model","isLikedByUser":false,"numParameters":937803241},{"author":"parler-tts","authorData":{"_id":"65d32204dd8292fdc69a11d9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62611fcabbcbd1c34f1615f6/derNQFLKSTg-Y-jMUCKtD.png","fullname":"Parler TTS","name":"parler-tts","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":331,"isUserFollowing":false},"downloads":268,"gated":false,"id":"parler-tts/parler-tts-tiny-v1","availableInferenceProviders":[],"lastModified":"2024-09-30T15:20:30.000Z","likes":3,"pipeline_tag":"text-to-speech","private":false,"repoType":"model","isLikedByUser":false,"numParameters":316555314},{"author":"parler-tts","authorData":{"_id":"65d32204dd8292fdc69a11d9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62611fcabbcbd1c34f1615f6/derNQFLKSTg-Y-jMUCKtD.png","fullname":"Parler TTS","name":"parler-tts","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":331,"isUserFollowing":false},"downloads":20,"gated":false,"id":"parler-tts/parler-large-v1-jenny","availableInferenceProviders":[],"lastModified":"2024-09-30T15:18:02.000Z","likes":0,"pipeline_tag":"text-to-speech","private":false,"repoType":"model","isLikedByUser":false,"numParameters":2333013362},{"author":"parler-tts","authorData":{"_id":"65d32204dd8292fdc69a11d9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62611fcabbcbd1c34f1615f6/derNQFLKSTg-Y-jMUCKtD.png","fullname":"Parler TTS","name":"parler-tts","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":331,"isUserFollowing":false},"downloads":2,"gated":false,"id":"parler-tts/parler-tiny-v1-jenny","availableInferenceProviders":[],"lastModified":"2024-09-30T15:17:24.000Z","likes":3,"pipeline_tag":"text-to-speech","private":false,"repoType":"model","isLikedByUser":false,"numParameters":316555314},{"author":"parler-tts","authorData":{"_id":"65d32204dd8292fdc69a11d9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62611fcabbcbd1c34f1615f6/derNQFLKSTg-Y-jMUCKtD.png","fullname":"Parler TTS","name":"parler-tts","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":331,"isUserFollowing":false},"downloads":179,"gated":false,"id":"parler-tts/parler-mini-v1-jenny","availableInferenceProviders":[],"lastModified":"2024-09-30T15:16:53.000Z","likes":1,"pipeline_tag":"text-to-speech","private":false,"repoType":"model","isLikedByUser":false,"numParameters":877842290},{"author":"parler-tts","authorData":{"_id":"65d32204dd8292fdc69a11d9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62611fcabbcbd1c34f1615f6/derNQFLKSTg-Y-jMUCKtD.png","fullname":"Parler TTS","name":"parler-tts","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":331,"isUserFollowing":false},"downloads":568,"gated":false,"id":"parler-tts/parler-tts-mini-expresso","availableInferenceProviders":[],"lastModified":"2024-05-21T17:17:04.000Z","likes":115,"pipeline_tag":"text-to-speech","private":false,"repoType":"model","isLikedByUser":false}],"paperPreviews":[],"spaces":[{"author":"parler-tts","authorData":{"_id":"65d32204dd8292fdc69a11d9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62611fcabbcbd1c34f1615f6/derNQFLKSTg-Y-jMUCKtD.png","fullname":"Parler TTS","name":"parler-tts","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":331,"isUserFollowing":false},"colorFrom":"blue","colorTo":"pink","createdAt":"2024-04-09T10:59:03.000Z","emoji":"🥖","id":"parler-tts/parler_tts","lastModified":"2025-11-18T12:10:26.000Z","likes":844,"pinned":true,"private":false,"sdk":"gradio","repoType":"space","runtime":{"stage":"RUNNING","hardware":{"current":"zero-a10g","requested":"zero-a10g"},"storage":null,"gcTimeout":172800,"replicas":{"current":1,"requested":1},"devMode":false,"domains":[{"domain":"parler-tts-parler-tts.hf.space","stage":"READY"}],"sha":"e19b27c8b09c2ba343d3c82b2f6af7ddfff7ee8c"},"shortDescription":"High-fidelity Text-To-Speech","title":"Parler-TTS","isLikedByUser":false,"ai_short_description":"Generate natural-sounding speech from text with voice control","ai_category":"Speech Synthesis","trendingScore":0,"tags":["gradio","region:us"],"featured":true},{"author":"parler-tts","authorData":{"_id":"65d32204dd8292fdc69a11d9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62611fcabbcbd1c34f1615f6/derNQFLKSTg-Y-jMUCKtD.png","fullname":"Parler TTS","name":"parler-tts","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":331,"isUserFollowing":false},"colorFrom":"red","colorTo":"blue","createdAt":"2024-05-10T15:26:43.000Z","emoji":"⚡","id":"parler-tts/parler-tts-expresso","lastModified":"2024-05-17T11:17:01.000Z","likes":92,"pinned":false,"private":false,"sdk":"gradio","repoType":"space","runtime":{"stage":"RUNNING","hardware":{"current":"zero-a10g","requested":"zero-a10g"},"storage":null,"gcTimeout":172800,"replicas":{"current":1,"requested":1},"devMode":false,"domains":[{"domain":"parler-tts-parler-tts-expresso.hf.space","stage":"READY"}],"sha":"76a0ee2944cebbc4f5b22e0f770e3eb75e282f4d"},"title":"Parler TTS Expresso","isLikedByUser":false,"ai_short_description":"Convert text to speech with emotion","ai_category":"Speech Synthesis","trendingScore":0,"tags":["gradio","region:us"],"featured":false}],"buckets":[],"numBuckets":0,"numDatasets":8,"numModels":13,"numSpaces":3,"lastOrgActivities":[],"acceptLanguages":["*"],"canReadRepos":false,"canReadSpaces":false,"blogPosts":[],"currentRepoPage":0,"filters":{},"paperView":false}">AI & ML interests
None defined yet.
Parler-TTS
Parler-TTS is a lightweight text-to-speech (TTS) model that can generate high-quality, natural sounding speech in the style of a given speaker (gender, pitch, speaking style, etc). It is a reproduction of work from the paper Natural language guidance of high-fidelity text-to-speech with synthetic annotations by Dan Lyth and Simon King, from Stability AI and Edinburgh University respectively.
Contrary to other TTS models, Parler-TTS is a fully open-source release. All of the datasets, pre-processing, training code, and weights are released publicly under a permissive license, enabling the community to build on our work and develop their own powerful TTS models. It consists in:
- The Parler-TTS library for using and training high-quality TTS models.
- The Data-Speech repository, for annotating speech characteristics in a large-scale setting.
- This organization, that contains the released datasets and weights.
🚨 Two new checkpoints, Parler-TTS Mini v1.1 and Large v1, are out! 🚨 Trained on 45k hours of narrated audio, they're better and faster than previous versions, and introduce speaker consistency across generations. Try them out here 🤗!