mirror of
https://github.com/Nezumi-2711/9router.git
synced 2026-09-22 13:38:31 +00:00
- image/embed/tts/search base URLs derive from media.*Config.baseUrl / searchViaChat.endpoint (single source); handlers read PROVIDER_MEDIA. - ~18 hardcoded endpoints moved: bfl/fal/stability/runway/hf/gemini/ cloudflare/recraft/sdwebui/comfyui/nanobanana image, voyage embed, gemini/openrouter tts, chatSearch endpoints. - Byte-identical: PROVIDERS 62 + alias 90 baselines, image buildUrl outputs. Co-authored-by: Cursor <cursoragent@cursor.com>
74 lines
2.3 KiB
JavaScript
74 lines
2.3 KiB
JavaScript
// OpenRouter TTS — via chat completions + audio modality (SSE stream)
|
|
import { PROVIDER_MEDIA } from "../../providers/index.js";
|
|
|
|
const TTS_CFG = PROVIDER_MEDIA["openrouter"]?.ttsConfig || {};
|
|
|
|
export default {
|
|
async synthesize(text, model, credentials) {
|
|
if (!credentials?.apiKey) throw new Error("No OpenRouter API key configured");
|
|
|
|
// model format: "tts-model/voice" e.g. "openai/gpt-4o-mini-tts/alloy"
|
|
let ttsModel = TTS_CFG.defaultModel;
|
|
let voice = "alloy";
|
|
if (model && model.includes("/")) {
|
|
const lastSlash = model.lastIndexOf("/");
|
|
const maybVoice = model.slice(lastSlash + 1);
|
|
const maybeModel = model.slice(0, lastSlash);
|
|
if (maybeModel.includes("/")) {
|
|
ttsModel = maybeModel;
|
|
voice = maybVoice;
|
|
} else {
|
|
voice = model;
|
|
}
|
|
} else if (model) {
|
|
voice = model;
|
|
}
|
|
|
|
const res = await fetch(TTS_CFG.baseUrl, {
|
|
method: "POST",
|
|
headers: {
|
|
"Content-Type": "application/json",
|
|
"Authorization": `Bearer ${credentials.apiKey}`,
|
|
...(TTS_CFG.headers || {}),
|
|
},
|
|
body: JSON.stringify({
|
|
model: ttsModel,
|
|
modalities: ["text", "audio"],
|
|
audio: { voice, format: "wav" },
|
|
stream: true,
|
|
messages: [{ role: "user", content: text }],
|
|
}),
|
|
});
|
|
|
|
if (!res.ok) {
|
|
const err = await res.json().catch(() => ({}));
|
|
throw new Error(err?.error?.message || `OpenRouter TTS failed: ${res.status}`);
|
|
}
|
|
|
|
// Parse SSE stream, accumulate base64 audio chunks
|
|
const chunks = [];
|
|
const reader = res.body.getReader();
|
|
const decoder = new TextDecoder();
|
|
let buffer = "";
|
|
|
|
while (true) {
|
|
const { done, value } = await reader.read();
|
|
if (done) break;
|
|
buffer += decoder.decode(value, { stream: true });
|
|
const lines = buffer.split("\n");
|
|
buffer = lines.pop();
|
|
for (const line of lines) {
|
|
if (!line.startsWith("data: ") || line === "data: [DONE]") continue;
|
|
try {
|
|
const json = JSON.parse(line.slice(6));
|
|
const audioData = json.choices?.[0]?.delta?.audio?.data;
|
|
if (audioData) chunks.push(audioData);
|
|
} catch {}
|
|
}
|
|
}
|
|
|
|
if (chunks.length === 0) throw new Error("OpenRouter TTS returned no audio data");
|
|
return { base64: chunks.join(""), format: "wav" };
|
|
},
|
|
};
|