{"id":"5051347e-f294-4788-97ed-f7c3bd1a1dc5","kind":"companies","code":"UB-C13321","name":"YourVoice","nameBasis":"source-english","summary":"Open-source local AI voice workbench and music generation | Offline dubbing, voice clone, and multi-track arrangement","description":"yovoice is a free, open-source fully local AI audio and music creation workbench (macOS, Windows, and Linux). Zero cloud cost, 100% offline privacy, no Python env setup. Supports voice clone, storyboard dubbing, speech synthesis, AI songs and SFX, and multi-track MIDI arrangement.","country":null,"category":null,"originalName":"YourVoice","eventDate":null,"website":"https://yovoice.leemysw.com/","sourceUpdatedAt":"2026-10-26T00:00:00.000Z","englishUpdatedAt":"2026-11-01T02:19:37.361Z","reviewedAt":"2026-11-01T02:19:37.361Z","snapshotAt":"2026-11-01T00:40:31.077Z","sourceHash":"83d21babf2cf6599f5a6c482818f4e35ba9a87d18dc579986ab97b6aa25f4f0a","companyId":null,"foundedYear":null,"logoUrl":null,"originalText":"开源本地 AI 语音工作台与音乐生成 | 离线配音、声音克隆与多轨编曲\n\nyovoice 是一款免费、开源的纯本地 AI 音频与音乐创作工作台（支持 macOS、Windows 与 Linux）。零云端费用，100% 离线隐私，免配置 Python 环境。支持声音克隆、故事分镜配音、语音合成、AI 歌曲与音效生成及多轨 MIDI 编曲。","sources":[],"related":[{"id":"416a91ab-a44a-4cfb-82bb-954d8f001d34","kind":"products","code":"UB-D6518","name":"YourVoice","nameBasis":"original-brand","summary":"Yovoice is a local AI dubbing, voice cloning and text-to-speech tool launched by leemysw. It is mainly targeted at video creators, podcast and audio content producers, developers and users who need to protect their voice data. It can convert transcripts into voices with emotion and expressiveness, and also supports replicating vocal lines by referring to audio or designing new sounds based on text descriptions. Users can enter lines in the Windows or macOS client, select a timbre and adjust the mood, tone and intonation to generate article readings, plot interpretations or video narrations. After the model is downloaded, speech synthesis can be run completely offline on the machine, and the manuscript, timbre, and generated works are saved locally by default; CLI and Agent Skills are also provided to facilitate batch dubbing or access to automated processes. Compared with online TTS tools, yovoice puts more emphasis on local operation, sound asset control and adjustable expression effects. Core function text-to-speech: input articles, lines or narration manuscripts, select a tone and generate playable speech, suitable for reading aloud, video dubbing and audio content production. Long-form and multi-character readings: Supports long texts and multi-character interpretations, and can configure different voices for different characters, which can be used in the production of novel fragments, scripts or plot content. Sound cloning and timbre design: Upload or record reference audio to extract your own voice, or design a new timbre that meets the requirements through text description.","description":"Yovoice is a local AI dubbing, voice cloning and text-to-speech tool launched by leemysw. It is mainly targeted at video creators, podcast and audio content producers, developers and users who need to protect their voice data. It can convert transcripts into voices with emotion and expressiveness, and also supports replicating vocal lines by referring to audio or designing new sounds based on text descriptions. Users can enter lines in the Windows or macOS client, select a timbre and adjust the mood, tone and intonation to generate article readings, plot interpretations or video narrations. After the model is downloaded, speech synthesis can be run completely offline on the machine, and the manuscript, timbre, and generated works are saved locally by default; CLI and Agent Skills are also provided to facilitate batch dubbing or access to automated processes. Compared with online TTS tools, yovoice puts more emphasis on local operation, sound asset control and adjustable expression effects. Core function text-to-speech: input articles, lines or narration manuscripts, select a tone and generate playable speech, suitable for reading aloud, video dubbing and audio content production. Long-form and multi-character readings: Supports long texts and multi-character interpretations, and can configure different voices for different characters, which can be used in the production of novel fragments, scripts or plot content. Sound cloning and timbre design: Upload or record reference audio to extract your own voice, or design a new timbre that meets the requirements through text description.","country":null,"category":"Audio editing","originalName":"YourVoice","eventDate":null,"website":null,"sourceUpdatedAt":"2026-10-26T21:00:17.269Z","englishUpdatedAt":"2026-10-28T00:56:06.894Z","reviewedAt":"2026-10-28T00:56:06.894Z","snapshotAt":"2026-10-28T00:47:51.550Z","sourceHash":"4d11bc4c156d9a62ffeebef195fcb644b6a103e530b24ed4fc3eab249f8a611a","companyId":"5051347e-f294-4788-97ed-f7c3bd1a1dc5","foundedYear":null,"logoUrl":null,"path":"/products/yourvoice"}],"finance":{"funding":{"metric":"funding","count":0,"latest":null,"years":[],"points":[],"linePoints":[],"conflictGroups":0,"omittedRecordCount":0,"records":[],"totalRaised":null},"valuation":{"metric":"valuation","count":0,"latest":null,"years":[],"points":[],"linePoints":[],"conflictGroups":0,"omittedRecordCount":0,"records":[]},"revenue":{"metric":"revenue","count":0,"latest":null,"years":[],"points":[],"linePoints":[],"conflictGroups":0,"omittedRecordCount":0,"records":[]}},"events":[],"team":[],"productsRelated":[{"id":"416a91ab-a44a-4cfb-82bb-954d8f001d34","kind":"products","code":"UB-D6518","name":"YourVoice","nameBasis":"original-brand","summary":"Yovoice is a local AI dubbing, voice cloning and text-to-speech tool launched by leemysw. It is mainly targeted at video creators, podcast and audio content producers, developers and users who need to protect their voice data. It can convert transcripts into voices with emotion and expressiveness, and also supports replicating vocal lines by referring to audio or designing new sounds based on text descriptions. Users can enter lines in the Windows or macOS client, select a timbre and adjust the mood, tone and intonation to generate article readings, plot interpretations or video narrations. After the model is downloaded, speech synthesis can be run completely offline on the machine, and the manuscript, timbre, and generated works are saved locally by default; CLI and Agent Skills are also provided to facilitate batch dubbing or access to automated processes. Compared with online TTS tools, yovoice puts more emphasis on local operation, sound asset control and adjustable expression effects. Core function text-to-speech: input articles, lines or narration manuscripts, select a tone and generate playable speech, suitable for reading aloud, video dubbing and audio content production. Long-form and multi-character readings: Supports long texts and multi-character interpretations, and can configure different voices for different characters, which can be used in the production of novel fragments, scripts or plot content. Sound cloning and timbre design: Upload or record reference audio to extract your own voice, or design a new timbre that meets the requirements through text description.","description":"Yovoice is a local AI dubbing, voice cloning and text-to-speech tool launched by leemysw. It is mainly targeted at video creators, podcast and audio content producers, developers and users who need to protect their voice data. It can convert transcripts into voices with emotion and expressiveness, and also supports replicating vocal lines by referring to audio or designing new sounds based on text descriptions. Users can enter lines in the Windows or macOS client, select a timbre and adjust the mood, tone and intonation to generate article readings, plot interpretations or video narrations. After the model is downloaded, speech synthesis can be run completely offline on the machine, and the manuscript, timbre, and generated works are saved locally by default; CLI and Agent Skills are also provided to facilitate batch dubbing or access to automated processes. Compared with online TTS tools, yovoice puts more emphasis on local operation, sound asset control and adjustable expression effects. Core function text-to-speech: input articles, lines or narration manuscripts, select a tone and generate playable speech, suitable for reading aloud, video dubbing and audio content production. Long-form and multi-character readings: Supports long texts and multi-character interpretations, and can configure different voices for different characters, which can be used in the production of novel fragments, scripts or plot content. Sound cloning and timbre design: Upload or record reference audio to extract your own voice, or design a new timbre that meets the requirements through text description.","country":null,"category":"Audio editing","originalName":"YourVoice","eventDate":null,"website":null,"sourceUpdatedAt":"2026-10-26T21:00:17.269Z","englishUpdatedAt":"2026-10-28T00:56:06.894Z","reviewedAt":"2026-10-28T00:56:06.894Z","snapshotAt":"2026-10-28T00:47:51.550Z","sourceHash":"4d11bc4c156d9a62ffeebef195fcb644b6a103e530b24ed4fc3eab249f8a611a","companyId":"5051347e-f294-4788-97ed-f7c3bd1a1dc5","foundedYear":null,"logoUrl":null,"path":"/products/yourvoice"}],"investors":[],"path":"/companies/yourvoice","structured":{"city":null,"country":null,"location":null,"role":null,"category":null,"company":null},"definition":"YourVoice is a company.","summaryBasis":"translated","thin":false,"canonical":"https://uniquebase.ai/companies/yourvoice"}