summaryrefslogtreecommitdiff
path: root/internal/audio/provider.go
diff options
context:
space:
mode:
authorPaul Buetow <paul@buetow.org>2026-04-02 16:36:25 +0300
committerPaul Buetow <paul@buetow.org>2026-04-02 16:36:25 +0300
commit6bd23a588bacee2e8c75f477150b7e2d345002ff (patch)
tree67bfa78afe206e7560350bdd52c60e0e80ec3243 /internal/audio/provider.go
parent6ce9123de04ffff961cbf1da73648679216ff637 (diff)
Release v0.9.0v0.9.0
Diffstat (limited to 'internal/audio/provider.go')
-rw-r--r--internal/audio/provider.go4
1 files changed, 2 insertions, 2 deletions
diff --git a/internal/audio/provider.go b/internal/audio/provider.go
index b7f6bd9..4fdccfb 100644
--- a/internal/audio/provider.go
+++ b/internal/audio/provider.go
@@ -33,7 +33,7 @@ type Config struct {
// Gemini-specific settings
GoogleAPIKey string
GeminiTTSModel string // "gemini-2.5-flash-preview-tts"
- GeminiVoice string // One of GeminiVoices, or empty for the model default.
+ GeminiVoice string // One of GeminiVoices; empty lets the caller choose a random voice.
GeminiSpeed float64 // Prompt hint for desired speech speed
}
@@ -42,7 +42,7 @@ func DefaultProviderConfig() *Config {
return &Config{
Provider: "gemini",
OutputDir: "./",
- OutputFormat: "wav",
+ OutputFormat: "mp3",
OpenAIModel: "gpt-4o-mini-tts", // New model with voice instructions support
OpenAIVoice: "alloy",
OpenAISpeed: 1.0,