{"id":35631719,"url":"https://github.com/yanorei32/aitalked-server","last_synced_at":"2026-05-30T01:04:05.960Z","repository":{"id":316702207,"uuid":"1064437327","full_name":"yanorei32/aitalked-server","owner":"yanorei32","description":"Simple VOICEROID / GynoidTalk Web Server based on aitalked library","archived":false,"fork":false,"pushed_at":"2026-05-20T01:42:04.000Z","size":253,"stargazers_count":1,"open_issues_count":1,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2026-05-20T04:43:09.415Z","etag":null,"topics":["aitalked","api","axum","gynoidtalk","japanese","japanese-tts","rust","text-to-speech","tts","voiceroid","voiceroid2","web"],"latest_commit_sha":null,"homepage":"","language":"Rust","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-2-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/yanorei32.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,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-09-26T03:22:02.000Z","updated_at":"2026-05-20T01:24:45.000Z","dependencies_parsed_at":"2025-09-26T08:18:54.436Z","dependency_job_id":"129cb5ca-bef8-441a-9784-1dffc94e3143","html_url":"https://github.com/yanorei32/aitalked-server","commit_stats":null,"previous_names":["yanorei32/aitalked-server"],"tags_count":126,"template":false,"template_full_name":null,"purl":"pkg:github/yanorei32/aitalked-server","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yanorei32%2Faitalked-server","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yanorei32%2Faitalked-server/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yanorei32%2Faitalked-server/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yanorei32%2Faitalked-server/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/yanorei32","download_url":"https://codeload.github.com/yanorei32/aitalked-server/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yanorei32%2Faitalked-server/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33676192,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-05-29T02:00:06.066Z","response_time":107,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["aitalked","api","axum","gynoidtalk","japanese","japanese-tts","rust","text-to-speech","tts","voiceroid","voiceroid2","web"],"created_at":"2026-01-05T09:11:26.775Z","updated_at":"2026-05-30T01:04:05.939Z","avatar_url":"https://github.com/yanorei32.png","language":"Rust","funding_links":[],"categories":[],"sub_categories":[],"readme":"# aitalked server\nThis is a lightweight web server designed for internal use with [Discord TTS](https://github.com/yanorei32/discord-tts), enabling headless synthesis of speech using VOICEROID and Gynoidtalk engines.\n\n\u003cimg width=\"1114\" height=\"823\" alt=\"image\" src=\"https://github.com/user-attachments/assets/4b42e24e-3873-4951-aa4b-93d2a8f2898f\" /\u003e\n\n\n## Features\n\n- 🗣️ **Headless Speech Synthesis**  \n  Utilizes the [aitalked](https://github.com/yanorei32/aitalked) crate to interface with `aitalked.dll`, allowing speech generation without GUI interaction.\n\n- 🔊 **Simple API Design**  \n  Offers a minimal HTTP API for generating speech. *Note: accent position editing is not supported due to API constraints.*\n\n- 📦 **WAV File Output**  \n  Returns synthesized speech as a WAV file in the HTTP response.\n\n- 🧠 **Character Info Extraction**  \n  Includes a feature to extract character infos from `info.bin`.\n\n## Use Case\n\nPrimarily intended for integration with Discord bots or automation tools requiring Japanese TTS capabilities in a headless environment.\n\n## API Details\n\n### `GET /api/voices`\n\nThis endpoint returns a list of available voice profiles that can be used with the TTS engine.\n\n#### Response\n\nThe response is a JSON array of voice objects. Each object contains:\n\n- `id` *(string)*: A unique identifier for the voice. This is used as the `voice_id` in the `/api/tts` request.\n- `name` *(string)*: The display name of the character or voice.\n- `icon` *(string)*: A base64-encoded PNG image representing the character's icon.\n- `dialect` *(string)*: Describes the regional dialect used by the voice (e.g., \"Standard\", \"Kansai\").\n- `gender` *(string)*: Indicates the gender of the voice (e.g., \"Male\", \"Female\").\n- `background_color` *(string)*: A hex color code representing the character's theme or UI background color.\n\nThis endpoint is useful for dynamically populating voice selection UIs or validating available options before making synthesis requests.\n\n### `POST /api/tts`\n\nThis endpoint generates speech audio from the provided text and voice parameters. It returns a WAV file upon success or a plain-text error message if the request is invalid.\n\n#### Request\n\nThe request must be a JSON object with the following fields:\n\n- `voice_id` *(string)*: The identifier of the voice character to use. This should match one of the IDs returned by the `/api/voices` endpoint.\n- `text` *(string)*: The input text to be synthesized into speech.\n- `is_kansai` *(boolean)* *(optional)*: If set to `true`, the generated speech will use Kansai dialect.\n- `volume` *(number)* *(optional)*: Controls the loudness of the voice. Typically ranges from 0 to 1 (maximum 5).\n- `speed` *(number)* *(optional)*: Adjusts the speaking rate. Lower values slow down the speech, higher values speed it up.\n- `pitch` *(number)* *(optional)*: Modifies the pitch of the voice. Useful for making the voice sound higher or deeper.\n- `range` *(number)* *(optional)*: Controls the pitch variation. A higher range adds more expressiveness.\n- `pause_middle` *(number)* *(optional)*: Sets the pause duration after commas or mid-sentence breaks.\n- `pause_long` *(number)* *(optional)*: Sets the pause duration after long breaks, such as semicolons.\n- `pause_sentence` *(number)* *(optional)*: Sets the pause duration at the end of sentences.\n\n#### Response\n\n- `200 OK`: Returns a WAV file containing the synthesized speech.\n- `400 BAD_REQUEST`: Returns a plain-text error message describing the issue (e.g., missing fields, invalid values).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyanorei32%2Faitalked-server","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fyanorei32%2Faitalked-server","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyanorei32%2Faitalked-server/lists"}