diff --git a/docs/asset-engine/services.yaml b/docs/asset-engine/services.yaml index 1b7facc..906cf6a 100644 --- a/docs/asset-engine/services.yaml +++ b/docs/asset-engine/services.yaml @@ -545,7 +545,7 @@ services: Microsoft's diffusion-based long-form multi-speaker TTS. Multi-minute scripts with speaker switching. Not for low-latency single-line use. category: tts - version: 1 + version: 2 host: irv-ml1 endpoint: http://10.100.79.3:8194/v1/audio/speech method: POST @@ -557,8 +557,11 @@ services: fields: - name: model type: select - options: [vibevoice] - default: vibevoice + options: [tts-1, tts-1-hd, vibevoice] + default: tts-1 + description: > + OpenAI-compatibility aliases all map to VibeVoice internally. + Wire default is tts-1 (verified against /openapi.json). - name: input type: textarea label: "Text (or Speaker N: ... script)" @@ -569,15 +572,38 @@ services: - name: voice type: select label: Voice - default: Carter + default: en-Carter_man description: > - Built-in: Carter, Davis, Emma, Frank, Grace, Mike, Samuel. - Custom: drop WAV/MP3/FLAC/M4A into /worktank/vibevoice/voices/, restart container. - Voice cloning training NOT released by Microsoft. + OpenAI presets: alloy, echo, fable, onyx, nova, shimmer. + VibeVoice presets: en-Alice_woman, en-Carter_man, en-Frank_man, + en-Mary_woman_bgm, en-Maya_woman, in-Samuel_man, zh-Anchen_man_bgm, + zh-Bowen_man, zh-Xinran_woman. + Custom: drop WAV/MP3/FLAC/M4A into /worktank/vibevoice/voices/, + restart container. Voice cloning training NOT released by Microsoft. + options: + - alloy + - echo + - fable + - onyx + - nova + - shimmer + - en-Alice_woman + - en-Carter_man + - en-Frank_man + - en-Mary_woman_bgm + - en-Maya_woman + - in-Samuel_man + - zh-Anchen_man_bgm + - zh-Bowen_man + - zh-Xinran_woman - name: response_format type: select - options: [wav, mp3] - default: wav + options: [wav, mp3, opus, flac, pcm] + default: mp3 + description: > + Wire default is mp3 (verified /openapi.json). All five values + confirmed by exercising the endpoint 2026-05-11; aac and m4a + fail with 500 despite OpenAPI not enforcing an enum, so excluded. - name: stream type: bool default: false