mirror of
https://github.com/tiennm99/goclaw.git
synced 2026-10-12 16:15:24 +00:00
viettranx
04a9938f4f
- HTTP synthesize + test-connection now read tenant tts.timeout_ms (default 120s, was hardcoded 15s/10s). Gemini client default also bumped 30s→120s so both layers align when tenant config unset. - Inline prefix "Speak naturally: " prepended to single-voice text; multi-speaker transcripts pass through unchanged. - ErrTextOnlyResponse sentinel for 400 "text generation" bodies; single-voice retries once with stronger prefix. Narrowed needle list avoids false positives on unrelated 400s. - SynthesizeWithFallbackAdapted now returns errors.Join so sentinel survives fallback chain; HTTP 422 mapping + locale-translated ForLLM in agent tool (EN/VI/ZH catalogs). - Default Gemini model bumped to gemini-3.1-flash-tts-preview.
20 lines
573 B
Go
20 lines
573 B
Go
package gemini
|
|
|
|
import "slices"
|
|
|
|
// geminiModels is the static catalog of supported Gemini TTS model IDs.
|
|
// Source: https://ai.google.dev/gemini-api/docs/speech-generation (April 2026)
|
|
var geminiModels = []string{
|
|
"gemini-3.1-flash-tts-preview",
|
|
"gemini-2.5-flash-preview-tts",
|
|
"gemini-2.5-pro-preview-tts",
|
|
}
|
|
|
|
// defaultModel is the model used when none is specified.
|
|
const defaultModel = "gemini-3.1-flash-tts-preview"
|
|
|
|
// isValidModel reports whether id is in the static model catalog.
|
|
func isValidModel(id string) bool {
|
|
return slices.Contains(geminiModels, id)
|
|
}
|