Skip to content
CallMissed
Book a demo

Explore CallMissed

Back to all models
Text to Speechvoice-agentsmultilingualindian-languages

Eleven v4

by ElevenLabs · Released Undisclosed

ElevenLabs' most emotive, highest-quality text-to-speech model. 91 languages including 12 Indian languages; audio tags such as [laughs] are performed. $0.8333 per 10K characters.

Text to Speech

Eleven v4

Powered by ElevenLabs · Neural TTS (ElevenLabs Eleven v4)

Context Window

N/A

Parameters

Undisclosed

Max Output

N/A

Category

Text to Speech

Overview

Eleven v4 is ElevenLabs' flagship speech model: the most emotive and natural output in its line, with exceptional voice cloning and support for natural multi-speaker dialogue. It speaks 91 languages, including Hindi, Bengali, Tamil, Telugu, Marathi, Gujarati, Kannada, Malayalam, Punjabi, Odia and Urdu and Assamese, and performs bracketed audio tags written into the text, such as [laughs], [whispers] or [sighs].

On CallMissed it is available on POST /v1/audio/speech and as a voice-agent voice (tts_model). Every ElevenLabs model shares one voice library: pass a premade name such as sarah (the default), george or brian, or any ElevenLabs voice ID from your own library, including cloned voices. Set language to a base code such as hi to fix the language and how numbers are read; speed clamps to 0.7–1.2.

Pricing

MetricPrice
Price /10K chars₹80.0000

1 credit = ₹1 ≈ US$0.0104 (US$1 = ₹96). Transparent per-call pricing — you pay only for what you call, with no per-seat charge or minimums.

Key Highlights

  • Premium narration, brand voices and agents where delivery matters most
  • 91 languages, one shared ElevenLabs voice library (21 premade voices or any ElevenLabs voice ID)
  • On POST /v1/audio/speech and as a voice-agent voice (tts_model)
  • Speed 0.7–1.2; mp3, wav, pcm, opus, mulaw and alaw output

Benchmarks

BenchmarkScore
Languages91
Voices21+
Price$0.8333
Latency~1.4 s to first audio in our tests (dialogue path)

Technical Details

  • Model ID is ElevenLabs' own (eleven_v4)
  • 91 languages; language takes a base ISO code such as hi
  • Voice: a premade name or any 20-character ElevenLabs voice ID, including cloned voices
  • Input up to 4096 characters; no SSML; audio tags such as [laughs] are performed
  • Paid plans only

Strengths

  • ElevenLabs' most emotive, highest-quality text-to-speech model
  • Cloned and library voices from your ElevenLabs account work as-is
  • Available on the speech endpoint and in voice agents

Limitations

  • Premade voices carry English accents; the language is enforced by the language parameter
  • No SSML; streaming is not supported on the speech endpoint
  • Paid plans only

Use Cases

Premium narration, brand voices and agents where delivery matters mostCustomer support and sales voice agentsSpoken notifications and IVR prompts

API Example

curl https://api.callmissed.com/v1/audio/speech \
  -H "Authorization: Bearer cm_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "eleven_v4",
    "voice": "sarah",
    "language": "hi",
    "input": "Namaste, main aapki kaise madad kar sakti hoon?"
  }' --output speech.mp3

Endpoint: POST /v1/audio/speech · Model ID: eleven_v4

Try Eleven v4 now

Get 1000 free API credits on signup. No credit card required.

Start free Book a DemoRead docs