Skip to main content
An agent’s perceived quality is dominated by three choices: how it sounds (TTS), how it understands you (STT), and how it thinks (LLM).

​
TTS — text to speech

Anyreach supports three TTS providers.

​
Cartesia Sonic-3

The default and recommended choice for most use cases.
FieldDefaultRange
Voice ID(provider-specific)100+ voices, 42 languages
Speed1.00.6 – 1.5
Volume1.00.5 – 2.0
Emotionneutralneutral, happy, sad, angry, surprised, curious
Strong points: low latency, large voice catalog, expressive emotion control.

​
ElevenLabs

Best for premium-sounding voices and voice cloning. Models: eleven_turbo_v2, eleven_turbo_v2_5
SettingDefault
Stability0.5
Similarity boost0.75
Speed1.0
Trade-off: slightly higher latency than Cartesia in our measurements; usually worth it if you’ve cloned a brand voice.

​
LiveKit Inference

Pass-through to any TTS available through LiveKit’s inference plane. Specify the model string explicitly. Useful if you have a contract with a provider not natively supported.

​
STT — speech to text

ProviderModelNotes
Deepgramnova-2-general, nova-3-generalDefault. Robust, low latency, English-strong
Gladiasolaria-1Strong multilingual + code-switching
AnyReach Default(auto)Resolves to a provider at runtime based on language
LiveKit Inferencecustom stringBring-your-own
Pick Deepgram nova-3-general for English-only agents. Pick Gladia solaria-1 when callers may switch languages mid-utterance (common in customer support). Use AnyReach Default if you don’t want to think about it.

​
LLM — the model that drives the conversation

ProviderModels
OpenAIgpt-4o, gpt-4.1
Azure OpenAIgpt-4o, gpt-4.1
Google Gemini 2.5flash, flash-lite, pro (with thinking_budget, top_p/top_k)
Cerebrasllama-3.3-70b, zai-glm-4.7
Vercel AI Gatewayany model slug, e.g. anthropic/claude-sonnet-4
LiveKit Inferencecustom model string

​
How to choose

  • Default: gpt-4o (Azure) — best quality-per-latency trade-off for most use cases
  • Lowest latency: Cerebras llama-3.3-70b — sub-second time to first token, good for high call volumes where latency dominates UX
  • Highest quality reasoning: gpt-4.1 — pick when the agent needs to follow complex multi-step instructions or reason about KB content carefully
  • Compliance: prefer Azure OpenAI variants if you have data-residency requirements

​
Stacks, fallbacks, and output format

A couple of structural choices apply across the stack:
  • Stack type. An agent uses either an stt_llm_tts pipeline (separate speech recognition, LLM, and speech synthesis) or a realtime stack. Most agents use the pipeline stack.
  • Fallbacks. Each of STT, LLM, and TTS accepts a model fallback list plus an on_failure policy (attempt_timeout, max_retry, retry_interval). If the primary model errors or times out, Anyreach fails over to the next model in the list.
  • Audio output format. TTS output format is set per channel — for example ElevenLabs emits pcm_8000 for telephony. You normally don’t touch this; the platform picks a sane format per channel.
Provider-specific extras worth knowing: Deepgram supports keywords/keyterms boosting (disabled in multi-language mode), and Gladia supports code-switching and a processing region (us-west/eu-west).

​
Latency budget

A natural-feeling conversation needs end-to-end response latency under ~800ms. Latency stacks roughly as: 
caller stops talking
  + STT finalization      (~150ms)
  + LLM TTFT              (~300-500ms)
  + TTS first audio       (~150-300ms)
= agent starts speaking
If your agent feels sluggish, the LLM is usually the culprit. Try Cerebras Llama before tuning anything else.

​
Where to set this

All of these live in the Purpose & Personality section (voice + language) and Advanced Instructions section (model overrides) on the agent edit page.