{"id":50266610,"url":"https://github.com/second-state/qwen3_audio_api","last_synced_at":"2026-05-27T14:11:47.116Z","repository":{"id":334792752,"uuid":"1142795073","full_name":"second-state/qwen3_audio_api","owner":"second-state","description":"OpenAI compatible API servers for the Qwen3 TTS models","archived":false,"fork":false,"pushed_at":"2026-05-19T22:10:58.000Z","size":235,"stargazers_count":82,"open_issues_count":3,"forks_count":13,"subscribers_count":2,"default_branch":"main","last_synced_at":"2026-05-20T01:39:23.837Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Rust","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/second-state.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":"2026-01-26T21:36:25.000Z","updated_at":"2026-05-19T22:11:02.000Z","dependencies_parsed_at":"2026-01-27T09:00:30.599Z","dependency_job_id":null,"html_url":"https://github.com/second-state/qwen3_audio_api","commit_stats":null,"previous_names":["juntao/qwen3_tts_api","second-state/qwen3_audio_api"],"tags_count":8,"template":false,"template_full_name":null,"purl":"pkg:github/second-state/qwen3_audio_api","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/second-state%2Fqwen3_audio_api","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/second-state%2Fqwen3_audio_api/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/second-state%2Fqwen3_audio_api/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/second-state%2Fqwen3_audio_api/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/second-state","download_url":"https://codeload.github.com/second-state/qwen3_audio_api/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/second-state%2Fqwen3_audio_api/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33569234,"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":"2026-05-27T02:00:06.184Z","response_time":53,"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":[],"created_at":"2026-05-27T14:11:43.736Z","updated_at":"2026-05-27T14:11:47.109Z","avatar_url":"https://github.com/second-state.png","language":"Rust","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Qwen3 Audio API\n\nOpenAI-compatible API servers for [Qwen3-TTS](https://github.com/QwenLM/Qwen3-TTS) and [Qwen3-ASR](https://github.com/QwenLM/Qwen3-ASR), enabling self-hosted text-to-speech and speech-to-text via the standard OpenAI audio endpoints:\n\n- `/v1/audio/speech` — Text-to-speech (TTS)\n- `/v1/audio/transcriptions` — Speech-to-text (ASR)\n\n## Implementations\n\n| Language | Directory | Status |\n|----------|-----------|--------|\n| Python | [python/](python/) | Available |\n| Rust | [rust/](rust/) | Available |\n\nThe **Python** implementation is a FastAPI server built on the `qwen-tts` and `qwen-asr` Python packages. See [python/README.md](python/README.md) for setup, Docker images, API reference, and usage examples.\n\nThe **Rust** implementation is a high-performance axum/tokio server built on the [qwen3_tts](https://github.com/second-state/qwen3_tts_rs) and [qwen3_asr](https://github.com/second-state/qwen3_asr_rs) Rust crates, with libtorch (Linux) and MLX (macOS Apple Silicon) backends. See [rust/README.md](rust/README.md) for setup, pre-built binaries, API reference, and usage examples.\n\n## Features\n\n- **Text-to-Speech (TTS)**: Generate natural speech from text using Qwen3-TTS models\n  - Multiple voice presets (Vivian, Ryan, Serena, etc.)\n  - Voice cloning from audio samples\n  - Multiple languages (English, Chinese, Japanese, Korean, and more)\n  - Multiple output formats (WAV, MP3, FLAC, Opus, AAC)\n\n- **Speech-to-Text (ASR)**: Transcribe audio to text using Qwen3-ASR models\n  - 30+ language support with auto-detection\n  - Accepts various audio formats (WAV, MP3, M4A, etc.)\n\n## Why\n\nThe purpose of these API servers is to provide self-hosted, free backend audio services for projects such as:\n\n- [OpenClaw](https://github.com/openclaw/openclaw) — AI agent\n- [EchoKit](https://github.com/second-state/echokit_server) — Voice AI device\n- [Olares](https://github.com/beclab/Olares) — Personal AI cloud OS\n- [GaiaNet](https://github.com/GaiaNet-AI/gaianet-node) — Incentivized AI agent network and marketplace\n\nAny application that speaks the OpenAI audio API can swap in this server as a drop-in replacement.\n\n## License\n\nSee [LICENSE](LICENSE).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsecond-state%2Fqwen3_audio_api","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsecond-state%2Fqwen3_audio_api","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsecond-state%2Fqwen3_audio_api/lists"}