​

Voice Configuration

​

Choosing a TTS Provider

​

Sarvam

• 10+ Indian languages (Hindi, Tamil, Telugu, Kannada, Bengali, Marathi, Gujarati, Malayalam, Punjabi, Odia)
• Native Indian English accents
• Code-switching support (Hindi-English, Tamil-English, etc.)
• Optimized for Indian telecom networks

• temperature (0.01–1.0, default 0.5) — assistant-style prosody. We default to 0.5; 0.6 is more expressive but adds prosody jitter on long turns.
• min_buffer_size (30–200 chars, default 50) — how much text to buffer before the first audio chunk emits. Lower = faster TTFA, more fragmented prosody.
• max_chunk_length (50–500 chars, default 150) — splits long sentences for streaming.

{
  "tts": {
    "provider": "sarvam",
    "model": "bulbul:v3",
    "voice": "shubh",
    "language": "hi-IN",
    "speed": 1.0
  }
}

​

Cartesia

• Sub-100ms latency
• Emotion and speed control mid-sentence
• Streaming word-level timestamps
• Multilingual support

{
  "tts": {
    "provider": "cartesia",
    "model": "sonic-2",
    "voice_id": "a0e99841-438c-4a64-b679-ae501e7d6091",
    "output_format": "pcm_16000",
    "speed": "normal",
    "emotion": ["positivity:high", "curiosity:medium"]
  }
}

​

Deepgram TTS

• Very low latency
• Simple API
• Competitive pricing
• Good for high-volume use cases

{
  "tts": {
    "provider": "deepgram",
    "model": "aura-asteria-en"
  }
}

​

ElevenLabs

• Ultra-realistic voices with natural emotion
• Voice cloning (use your own voice)
• 29+ languages
• Extensive voice library

{
  "tts": {
    "provider": "elevenlabs",
    "voice_id": "21m00Tcm4TlvDq8ikWAM",
    "model": "eleven_turbo_v2_5",
    "stability": 0.5,
    "similarity_boost": 0.75
  }
}

​

Rime

• Consistent voice quality across calls
• Good pronunciation accuracy
• Fast inference
• Simple integration

{
  "tts": {
    "provider": "rime",
    "model": "mist",
    "voice": "cove",
    "speed": 1.0
  }
}

​

Inworld

• Character-consistent voices
• Emotional expressiveness
• Real-time voice modulation
• Persona-driven design

{
  "tts": {
    "provider": "inworld",
    "model": "inworld-v2",
    "voice": "default",
    "emotion": "friendly"
  }
}

​

Google Cloud TTS

• 220+ voices across 40+ languages
• Neural2 and Studio voices for premium quality
• SSML support
• Predictable pricing

{
  "tts": {
    "provider": "google",
    "voice_name": "en-US-Neural2-F",
    "language_code": "en-US",
    "speaking_rate": 1.0,
    "pitch": 0.0
  }
}

​

Azure Speech

• High-quality neural voices
• Custom neural voice training
• SSML with extensive control
• Strong enterprise compliance

{
  "tts": {
    "provider": "azure",
    "voice_name": "en-US-JennyNeural",
    "style": "friendly",
    "speaking_rate": "1.0"
  }
}

​

Provider Comparison

​

Voice Selection and Customization

​

Selecting a Voice in the Dashboard

1. Open your voice agent configuration.
2. Go to the Voice tab.
3. Select a TTS provider.
4. Browse available voices and click Preview to hear samples.
5. Adjust settings (speed, pitch, stability) with the sliders.
6. Click Save.

​

Voice Selection via API

curl -X PATCH "https://api.thinnest.ai/agents/agent_xyz" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "voice_config": {
      "tts_provider": "elevenlabs",
      "tts_voice_id": "21m00Tcm4TlvDq8ikWAM",
      "tts_model": "eleven_turbo_v2_5",
      "tts_stability": 0.5,
      "tts_similarity_boost": 0.75
    }
  }'

​

Matching Voice to Use Case

​

Speech-to-Text (STT) Configuration

​

Deepgram (Default)

{
  "stt": {
    "provider": "deepgram",
    "model": "nova-3",
    "language": "en-US",
    "punctuate": true,
    "smart_format": true,
    "profanity_filter": false
  }
}

​

Sarvam STT

{
  "stt": {
    "provider": "sarvam",
    "model": "saarika:v2",
    "language": "hi-IN"
  }
}

​

Google Speech-to-Text

{
  "stt": {
    "provider": "google",
    "model": "telephony",
    "language": "en-US",
    "denoiser": true
  }
}

​

Azure Speech-to-Text

{
  "stt": {
    "provider": "azure",
    "model": "default",
    "language": "en-US"
  }
}

​

Cartesia STT

{
  "stt": {
    "provider": "cartesia",
    "model": "ink",
    "language": "en"
  }
}

​

AssemblyAI

{
  "stt": {
    "provider": "assemblyai",
    "model": "best",
    "language": "en"
  }
}

​

STT Provider Comparison

​

Multi-Language Support

{
  "stt": {
    "language": "multi",
    "detect_language": true,
    "supported_languages": ["en", "es", "fr", "hi", "ta"]
  }
}

​

Turn Detection Mode

​

Your choice is respected

​

Configuration via API

{
  "voice_config": {
    "turn_detection_mode": "stt_endpointing",
    "min_silence_duration": 0.3,
    "min_speech_duration": 0.1,
    "min_endpointing_delay": 300,
    "max_endpointing_delay": 1.5
  }
}

​

STT/TTS Fallback

​

How Fallback Works

1. The agent sends audio to the primary provider.
2. If the primary provider fails (timeout, error, or degraded quality), the system automatically switches to the fallback provider.
3. The switch is seamless — callers experience a brief pause at most, not a dropped call.

​

Configuring TTS Fallback

{
  "tts": {
    "provider": "elevenlabs",
    "model": "eleven_turbo_v2_5",
    "voice_id": "21m00Tcm4TlvDq8ikWAM",
    "fallback": {
      "provider": "aero",
      "model": "aero-2",
      "voice": "maya"
    }
  }
}

​

Configuring STT Fallback

{
  "stt": {
    "provider": "deepgram",
    "model": "nova-3",
    "fallback": {
      "provider": "google",
      "model": "telephony"
    }
  }
}

​

Recommended Fallback Pairs

​

Noise Cancellation

​

Hush — install notes

hush_model/
├── lib/
├── onnx/
└── model_best.ckpt

​

Configuration via API

{
  "voice": {
    "noise_cancellation": "hush"
  }
}

​

Voice Style Preamble

• 1–2 short sentences per reply (~30 words)
• Use contractions (“I’m”, “you’re”)
• Never use markdown, bullets, headings, code blocks, or symbols
• Spell out currency, dates, units (“twenty dollars”, not “$20”)
• Don’t read URLs or email addresses character by character
• Ask one question at a time

​

Editing the preamble

​

Configuration via API

{
  "hooks": {
    "voice_style_preamble": {
      "enabled": true,
      "text": ""
    }
  }
}

• enabled: false — skip the preamble entirely
• text: "" (or omitted) — use the built-in default
• text: "<custom text>" — use your text instead of the default

​

Interruption Handling

​

Modes

{
  "interruption": {
    "enabled": true,
    "sensitivity": "medium"
  }
}

{
  "interruption": {
    "enabled": false
  }
}

​

Sensitivity Levels

​

Per-Message Interruption Control

When reading the terms and conditions, do not allow interruptions.
For all other responses, allow normal interruptions.

​

Silent Timeout Settings

{
  "timeouts": {
    "silence_timeout_seconds": 10,
    "silence_prompt": "Are you still there? I'm happy to help if you have any questions.",
    "max_silence_prompts": 2,
    "disconnect_after_max_silence": true,
    "disconnect_message": "It seems like you may have stepped away. Feel free to call back anytime. Goodbye!"
  }
}

​

Recommended Timeout Settings

​

Wait Before Speaking

​

When to tune

​

Configuration via API

{
  "voice_config": {
    "wait_before_speak_seconds": 0.4
  }
}

​

Voice Formatting and Pronunciation

​

Pronunciation Overrides

{
  "pronunciation": {
    "overrides": [
      {
        "word": "thinnestAI",
        "pronunciation": "thin-est A.I."
      },
      {
        "word": "PostgreSQL",
        "pronunciation": "post-gres-Q-L"
      },
      {
        "word": "API",
        "pronunciation": "A.P.I."
      }
    ]
  }
}

​

Number and Date Formatting

{
  "formatting": {
    "phone_numbers": "digit_by_digit",
    "currency": "natural",
    "dates": "natural",
    "times": "12_hour"
  }
}

​

Filler Words and Pauses

​

Instant Filler Words

{
  "fillerWordsEnabled": true,
  "fillerWords": ["hmm", "aha", "um", "okay"],
  "fillerWordsMinChars": 10,
  "fillerMinTtftMs": 800
}

• fillerWordsEnabled — Master toggle. Default true for new agents.
• fillerWords — Custom filler words. Leave empty to use language-appropriate defaults:
  • English — hmm, uh huh, um, right, okay
  • Hindi — hmm, acchha, haan, theek hai, ji
  • Other — hmm, aha, um, okay
• fillerWordsMinChars — Skip the filler when the user’s transcript is shorter than this. Default 10. Stops “yes” / “no” replies from getting an unnecessary “hmm” in front.
• fillerMinTtftMs — Collision guard. Only fire the filler if the previous turn’s LLM TTFT was at least this slow (in ms). Default 800. On a fast turn (TTFT < 800 ms) the real reply would arrive before the filler audio finishes, causing audio overlap even with cross-fade enabled. The first turn always probes (no prior TTFT data to gate on).

​

Thinking Phrases

{
  "silenceFillersEnabled": true,
  "silenceFillerPhrases": [
    "Let me check that for you.",
    "One moment please.",
    "Good question, let me look into that."
  ]
}

​

Turn Detection

​

Adaptive EOU Confidence

• Higher (0.85–0.95) — waits for more certainty before ending the turn. Fewer mid-thought cut-offs; the agent is more patient. Good for hesitant callers, technical Q&A, and IVRs that read out long IDs.
• Lower (0.40–0.60) — snappier. The agent responds faster but is more likely to interrupt a thought-pause. Good for terse, transactional chitchat.
• 0.70 (default) is balanced and works for most agents.

​

Smart Interruption

​

Proactive Re-engagement

• Pause delay (1.5–8.0 s) — how long the caller can pause mid-thought before the agent nudges. Default 3.0 s.
• Max nudges per pause (1–3) — cap so the agent doesn’t keep prodding. Default 1.
• Explicit phrases (optional) — leave empty for an LLM-generated nudge in the caller’s language. Adding phrases here locks the wording and is not auto-translated.

​

Testing Your Configuration

1. Use the web call test — Click Test Call in the dashboard to hear your changes immediately.
2. Test edge cases — Try interrupting, staying silent, speaking quickly, and using unusual words.
3. Test on a real phone — Web call audio quality differs from phone audio. Always test over a real phone line before going live.
4. Compare providers — Try the same conversation with different TTS providers to find the best fit.
5. Get feedback — Have someone unfamiliar with the system test the call and provide honest feedback.

​

Next Steps

• Inbound Calls — Apply your voice configuration to inbound call handling
• Outbound Calls — Use your configured voice for outbound campaigns
• Call Recording — Record calls to review voice quality over time