{"id":17366956,"url":"https://github.com/gabrielrf/voice2text","last_synced_at":"2025-09-20T19:31:04.970Z","repository":{"id":184101838,"uuid":"670282887","full_name":"GabrielRF/Voice2Text","owner":"GabrielRF","description":"Descrição automática de mensagens de voz em conversas privadas no Telegram","archived":false,"fork":false,"pushed_at":"2023-08-16T18:37:09.000Z","size":58,"stargazers_count":6,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2024-12-31T11:23:41.223Z","etag":null,"topics":["automation","openai","openai-whisper","pyrogram","telegram","transcription","whisper"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/GabrielRF.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-07-24T17:40:36.000Z","updated_at":"2023-12-08T15:50:47.000Z","dependencies_parsed_at":"2024-11-11T17:47:26.059Z","dependency_job_id":null,"html_url":"https://github.com/GabrielRF/Voice2Text","commit_stats":{"total_commits":8,"total_committers":2,"mean_commits":4.0,"dds":0.125,"last_synced_commit":"d957c953873c1c68a691911cbd1728ccfac52733"},"previous_names":["gabrielrf/voice2text"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GabrielRF%2FVoice2Text","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GabrielRF%2FVoice2Text/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GabrielRF%2FVoice2Text/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GabrielRF%2FVoice2Text/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/GabrielRF","download_url":"https://codeload.github.com/GabrielRF/Voice2Text/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":233682525,"owners_count":18713554,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["automation","openai","openai-whisper","pyrogram","telegram","transcription","whisper"],"created_at":"2024-10-15T22:12:30.084Z","updated_at":"2025-09-20T19:30:59.663Z","avatar_url":"https://github.com/GabrielRF.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cimg align=\"right\" alt=\"Voice2Text Logo\" width=\"30%\" height=\"auto\" src=\"https://github.com/GabrielRF/Voice2Text/blob/master/voice2text.jpg?raw=true\"\u003e\n\n# Voice2Text\n\nAutomação em conta do Telegram para transcrever áudios em conversas privadas. [Leia mais no post](https://blog.gabrf.com/posts/WhisperPyrogram/).\n\n## Voice2Text.py\n\n### Credenciais\n\n`api_id`: Obter em https://my.telegram.org/apps;\n\n`api_hash`: Obter em https://my.telegram.org/apps.\n\n### Modelo\n\nEscolha o modelo usado na transcrição. O valor padrão é `base`. [Escolha o modelo no repositório oficial](https://github.com/openai/whisper#available-models-and-languages).\n\n```python\nmodel = whisper.load_model(\"base\")\n```\n\n### Funções\n\n`remove_file`: Remove o arquivo de áudio para diminuir o uso de armazenamento;\n\n`voice_to_text`: Faz a transcrição do arquivo recebido em até 5 tentativas. Idioma selecionado: `Português`;\n\n`download_voice`: Salva o arquivo de áudio;\n\n`edit_message`: Edita a mensagem de texto. Usada ao finalizar a transcrição;\n\n`send_message`: Envia uma mensagem de texto indicando o início da transcrição;\n\n`delete_message`: Remove a mensagem de texto. Usada em caso de falha na transcrição;\n\n`receive_voice`: Recebe a mensagem com base nos filtros definidos e executa a transcrição.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgabrielrf%2Fvoice2text","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgabrielrf%2Fvoice2text","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgabrielrf%2Fvoice2text/lists"}