luulam/9router
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(tts): resolve Gemini TTS models from catalog

Browse Source 
Resolve Gemini TTS models from shared TTS catalog and provider registry
with a safe fallback, fixing requests resolving to models/undefined when
ttsConfig.models is empty. Add gemini-3.1-flash-tts-preview to catalogs.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
nguyenha935
2026-06-26 10:31:22 +07:00
committed by decolua
parent 644bff4cdd
commit ce844899ed
4 changed files with 109 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
open-sse/config/ttsModels.js
View File

@@ -96,10 +96,12 @@ export const TTS_MODELS_CONFIG = {
},
gemini: {
models: [
{ id: "gemini-3.1-flash-tts-preview", name: "Gemini 3.1 Flash TTS", type: "tts" },
{ id: "gemini-2.5-flash-preview-tts", name: "Gemini 2.5 Flash TTS", type: "tts" },
{ id: "gemini-2.5-pro-preview-tts", name: "Gemini 2.5 Pro TTS", type: "tts" },
],
voices: {
"gemini-3.1-flash-tts-preview": GEMINI_VOICES,
"gemini-2.5-flash-preview-tts": GEMINI_VOICES,
"gemini-2.5-pro-preview-tts": GEMINI_VOICES,
},

14
open-sse/handlers/ttsProviders/gemini.js
View File

@@ -1,11 +1,19 @@
// Gemini TTS — generateContent with AUDIO modality returns PCM L16, wrap as WAV
import { Buffer } from "node:buffer";
import { PROVIDER_MEDIA } from "../../providers/index.js";
import { PROVIDER_MEDIA, PROVIDER_MODELS } from "../../providers/index.js";
const TTS_CFG = PROVIDER_MEDIA["gemini"]?.ttsConfig || {};
const TTS_BASE = TTS_CFG.baseUrl;
const KNOWN_MODELS = (TTS_CFG.models || []).map((m) => m.id);
const DEFAULT_MODEL = KNOWN_MODELS[0];
const FALLBACK_MODEL = "gemini-3.1-flash-tts-preview";
const KNOWN_MODELS = [
...(TTS_CFG.models || []),
...(PROVIDER_MODELS["gemini-tts-models"] || []),
...(PROVIDER_MODELS.gemini || []).filter((m) => (m.kind || m.type) === "tts"),
]
.map((m) => m?.id)
.filter(Boolean)
.filter((id, index, list) => list.indexOf(id) === index);
const DEFAULT_MODEL = KNOWN_MODELS[0] || FALLBACK_MODEL;
const DEFAULT_VOICE = "Kore";
// Parse "model/voice" — if input doesn't match a known TTS model, treat it as voice with default model

1
open-sse/providers/registry/gemini.js
View File

@@ -52,6 +52,7 @@ export default {
{ id: "gemini-2.5-flash", name: "Gemini 2.5 Flash", params: ["language","prompt"], kind: "stt" },
{ id: "gemini-2.5-flash-lite", name: "Gemini 2.5 Flash Lite (Cheapest)", params: ["language","prompt"], kind: "stt" },
{ id: "gemini-2.0-flash", name: "Gemini 2.0 Flash", params: ["language","prompt"], kind: "stt" },
{ id: "gemini-3.1-flash-tts-preview", name: "Gemini 3.1 Flash TTS", kind: "tts" },
{ id: "gemini-2.5-flash-preview-tts", name: "Gemini 2.5 Flash TTS", kind: "tts" },
{ id: "gemini-2.5-pro-preview-tts", name: "Gemini 2.5 Pro TTS", kind: "tts" },
{ id: "embedding-001", name: "Embedding 001", dimensions: 768, kind: "embedding" },