tbenandClaude Opus 5.5
bc499a7466
The Speech section of every model settings form now has "Hear a sample", which streams a short sentence (AppData.VoicePreviewText) in the form's model and voice before they're saved, through GET api/admin/harness/preview-voice (super admins and admins, that model only via grabModelCandidate). pickVoice is shared with speakText, and explainAudioError reads why a streamed player failed for both read-aloud and the sample. Co-Authored-By: Claude Opus 5.5 <[email protected]>
85 lines
2.4 KiB
TypeScript
85 lines
2.4 KiB
TypeScript
import grabHarnessSetting from "@/src/functions/backend/db/harness/grab-harness-setting";
|
|
import grabHarnessAdapter from "../providers/grab-harness-adapter";
|
|
import resolveHarnessCandidates from "../resolve/resolve-harness-candidates";
|
|
import withCandidates from "../resolve/with-candidates";
|
|
import type { HarnessCandidate } from "../types";
|
|
|
|
type Params = {
|
|
text: string;
|
|
/**
|
|
* `mp3` unless set.
|
|
*/
|
|
format?: string;
|
|
signal?: AbortSignal;
|
|
/**
|
|
* Uses this bot's speech model and voice when it has its own.
|
|
*/
|
|
bot_id?: number | string;
|
|
/**
|
|
* The workspace the call is in: its models win over the bot's.
|
|
*/
|
|
workspace_id?: number | string | null;
|
|
};
|
|
|
|
/**
|
|
* Reads text aloud with the speech harness, as a stream that can play
|
|
* while the rest is still being made. Falls back to the next model only
|
|
* until one answers. Uses the voice picked in the speech setting when the
|
|
* model has it, else the model's first voice.
|
|
*/
|
|
export default async function speakText({
|
|
text,
|
|
format,
|
|
signal,
|
|
bot_id,
|
|
workspace_id,
|
|
}: Params) {
|
|
const [candidates, setting] = await Promise.all([
|
|
resolveHarnessCandidates({ harness: "speech", bot_id, workspace_id }),
|
|
grabHarnessSetting({ harness: "speech", bot_id, workspace_id }),
|
|
]);
|
|
|
|
const { result } = await withCandidates({
|
|
harness: "speech",
|
|
candidates,
|
|
run: async (candidate) =>
|
|
await grabHarnessAdapter({ kind: candidate.provider.kind }).speak({
|
|
candidate,
|
|
text,
|
|
voice: pickVoice({
|
|
candidate,
|
|
voice:
|
|
typeof setting.options.voice == "string"
|
|
? setting.options.voice
|
|
: undefined,
|
|
}),
|
|
format,
|
|
signal: signal || new AbortController().signal,
|
|
}),
|
|
});
|
|
|
|
return result;
|
|
}
|
|
|
|
/**
|
|
* The voice to ask for: the picked one when the model has it (or the
|
|
* model was picked by hand), else the model's first, else OpenAI's.
|
|
*/
|
|
export function pickVoice({
|
|
candidate,
|
|
voice,
|
|
}: {
|
|
candidate: HarnessCandidate;
|
|
voice?: string;
|
|
}) {
|
|
const voices = candidate.model.voices;
|
|
|
|
if (voice && (candidate.source == "pinned" || voices?.includes(voice))) {
|
|
return voice;
|
|
}
|
|
|
|
if (voices?.[0]) return voices[0];
|
|
|
|
return candidate.provider.kind == "openai" ? "alloy" : undefined;
|
|
}
|