Text to Speech (TTS)

Convert written text into natural-sounding speech using AI voices.

Perfect for dialogue, narration, accessibility, or dynamic voice-over content — powered by ElevenLabs and other TTS providers.

---

✅ Basic Usage

AudioClip voice = await "Welcome to the future of AI voices."
    .GENSpeech()
    .SetModel(ElevenLabsModel.VoiceV2)
    .SetVoice(ElevenLabsVoice.Rachel)
    .SetSpeed(1.0f)
    .ExecuteAsync();

🔉 You’ll receive a Unity AudioClip, ready for playback or saving.

---

⚙️ Configuration Options

Method	Description
SetVoice(GenAIVoice)	Choose which AI voice to use (e.g., ElevenLabsVoice.Rachel)
SetSpeed(float)	Playback speed multiplier (e.g., 1.0 = normal)
SetSeed(uint)	Optional: generate deterministic output
SetOutputPath(path)	Save audio to specific path
SetOutputFormat(format)	Output format (MP3, WAV, PCM, etc.) — ElevenLabs only
SetModel(model)	Set the model (optional — defaults from settings)

---

🚀 Streaming TTS

Play audio in real-time as it’s generated — ideal for chat avatars or quick feedback loops.

await "Loading complete."
    .GENSpeech()
    .SetVoice(ElevenLabsVoice.Adam)
    .StreamAsync(myStreamAudioPlayer);

🎧 StreamAudioPlayer is a component that plays incoming audio chunks as they arrive.

---

📦 Output Formats (ElevenLabs)

Use .SetOutputFormat(...) to control file type:

Format	Description
OutputFormat.MPEG	Compact .mp3 format (default)
OutputFormat.PCM_S16LE_16	Raw PCM, 16-bit, mono, 16kHz
OutputFormat.WAV	Lossless .wav format (useful for editing)

---

🧠 Tips

• Voices vary by provider. You can define your own GenAIVoice or use built-in constants.

• For Unity playback, use .AsAudioClip() or .Play() extension methods.

• If your TTS result sounds unnatural, try adjusting temperature, seed, or choosing a different voice.