Voices

Every agent speaks through a Text-to-Speech (TTS) engine that converts the LLM’s text response into audio in real time. TruGen ships with ElevenLabs and Cartesia as the default providers — both deliver sub-150 ms first-audio latency across dozens of languages and voice styles. The voice is configured per agent via voice_id. Copy an ID from the Voice Library and drop it into your agent config.

Setting a voice

Set voice_id when you create or update an agent. Everything else — provider, model, sample rate, encoding — falls back to platform defaults if omitted.

{
  "agent_name": "Support Agent",
  "avatars": [
    {
      "avatar_key_id": "665a1170",
      "tts": {
        "voice_id": "FGY2WhTYpPnrIDTdsKH5"
      }
    }
  ]
}

You can also change the voice directly from the Create New Agent form in the Developer Portal — no code required.

Full TTS configuration

For advanced use — custom pronunciations, sample rate, pitch, speaking rate, stability — pass a full tts object:

"tts": {
  "provider": "elevenlabs",
  "model_id": "eleven_turbo_v2_5",
  "voice_id": "FGY2WhTYpPnrIDTdsKH5",
  "language": "a",
  "speaking_rate": 1.0,
  "stability": 0.5,
  "similarity_boost": 0.75,
  "sample_rate": 16000,
  "encoding": "pcm_s16le",
  "fallback_voice_id": "am_puck",
  "customPronounciation": [
    { "word": "TRUGEN", "pronounciation": "TRUE GEN" },
    { "word": "SQL",    "pronounciation": "Sequel" }
  ]
}

See the full agent configuration reference for every field.

Choosing a voice

Goal	Recommendation
Professional, corporate tone	Chris, Will, Evan
Warm, conversational tone	Rachel, Laura, Hope
Broad multilingual coverage	Any voice with `language: "multi"` — providers auto-adapt
Regional accent	Yatin (South Asian), Omar (Middle Eastern)
Fastest first-audio latency	Cartesia Sonic voices

Choosing a TTS provider

Provider	Model	Best for
ElevenLabs	`eleven_turbo_v2_5`	Multilingual, expressive default
ElevenLabs	`eleven_turbo_v2`	English-first with slightly lower latency
Cartesia	`sonic-3.5`	Ultra-low latency real-time conversations
Cartesia	`sonic-3`	Fastest voice quality trade-off

Full provider list in Providers.

Custom pronunciations

Product names, acronyms, and industry jargon often get mispronounced. Fix them per-voice by adding entries to customPronounciation:

"customPronounciation": [
  { "word": "TRUGEN",  "pronounciation": "TRUE GEN" },
  { "word": "API",     "pronounciation": "A P I" },
  { "word": "SQL",     "pronounciation": "Sequel" },
  { "word": "GraphQL", "pronounciation": "Graph Q L" }
]

Pronunciations apply to whichever voice is set on the agent. For dictionaries shared across many agents, see pronunciation dictionaries (coming soon).

Fallback voices

If the primary TTS provider fails or is rate-limited, TruGen falls back to a secondary voice automatically. Set fallback_voice_id to a voice from a different provider for resilience:

"tts": {
  "provider": "elevenlabs",
  "voice_id": "FGY2WhTYpPnrIDTdsKH5",
  "fallback_voice_id": "am_puck"
}

Voice cloning

For a fully custom voice — a spokesperson, a specific character, or your CEO — TruGen supports voice cloning through ElevenLabs Professional Voice Cloning. Contact sales@trugen.ai or provide an existing PVC voice ID directly as voice_id.

Introduction

Models

AI Teammates (Avatars)

Text to Video

Setting a voice

Full TTS configuration

Choosing a voice

Choosing a TTS provider

Custom pronunciations

Fallback voices

Voice cloning

What’s next

Voice Library

Multilingual

​Setting a voice

​Full TTS configuration

​Choosing a voice

​Choosing a TTS provider

​Custom pronunciations

​Fallback voices

​Voice cloning

​What’s next

Voice Library

Multilingual

Setting a voice

Full TTS configuration

Choosing a voice

Choosing a TTS provider

Custom pronunciations

Fallback voices

Voice cloning

What’s next