diff options
| author | Paul Buetow <paul@buetow.org> | 2025-07-19 22:27:13 +0300 |
|---|---|---|
| committer | Paul Buetow <paul@buetow.org> | 2025-07-19 22:27:13 +0300 |
| commit | 44cf5eee8fba096496f0704cec44fd436ecb5c2e (patch) | |
| tree | 5596a40ebaeb3e30f2bb210b321a573110f1a997 /internal/audio | |
| parent | d663a312ff5f45513a23adf9eb9ffb29377bbad9 (diff) | |
feat: update default voice to alloy with speed 0.98
- Changed default voice from 'nova' to 'alloy'
- Changed default speed from 0.9 to 0.98 for better clarity
- GUI now uses default voice/speed for first generation
- Regeneration still uses random voice/speed for variety
π€ Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Diffstat (limited to 'internal/audio')
| -rw-r--r-- | internal/audio/provider.go | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/internal/audio/provider.go b/internal/audio/provider.go index fd47ef4..53b08c1 100644 --- a/internal/audio/provider.go +++ b/internal/audio/provider.go @@ -42,8 +42,8 @@ func DefaultProviderConfig() *Config { OutputDir: "./", OutputFormat: "mp3", OpenAIModel: "gpt-4o-mini-tts", // New model with voice instructions support - OpenAIVoice: "nova", - OpenAISpeed: 0.9, // Slightly slower for clarity (note: may be ignored by gpt-4o-mini-tts) + OpenAIVoice: "alloy", + OpenAISpeed: 0.98, // Default speed for clarity OpenAIInstruction: "You are speaking Bulgarian language (Π±ΡΠ»Π³Π°ΡΡΠΊΠΈ Π΅Π·ΠΈΠΊ). Pronounce the Bulgarian text with authentic Bulgarian phonetics, not Russian. Speak slowly and clearly for language learners.", EnableCache: true, CacheDir: "./.audio_cache", |