Skip to content
CallMissed
Book a demo

Explore CallMissed

Back to all models
Text to Speechvoice-agentsmultilingualindian-languages

Eleven Multilingual v2

by ElevenLabs · Released Undisclosed

ElevenLabs' lifelike, consistent-quality model, the most stable on long-form speech. 29 languages including Hindi and Tamil. $0.8333 per 10K characters.

Text to Speech

Eleven Multilingual v2

Powered by ElevenLabs · Neural TTS (ElevenLabs Eleven Multilingual v2)

Context Window

N/A

Parameters

Undisclosed

Max Output

N/A

Category

Text to Speech

Overview

Eleven Multilingual v2 is ElevenLabs' lifelike, emotionally rich model and the most stable choice for long generations: voice-overs, audiobooks, e-learning and narration. It speaks 29 languages, including English, Hindi, Tamil, Japanese, Chinese, German, French, Spanish, Portuguese, Arabic and Korean, and reads the language from the text itself, so the language parameter is not used.

Available on POST /v1/audio/speech and as a voice-agent voice; shares the ElevenLabs voice library (sarah default, or any ElevenLabs voice ID).

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

  • Narration, audiobooks and voice-overs
  • 29 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
Languages29
Voices21+
Price$0.8333
Latency~0.75 s to first audio in our tests

Technical Details

  • Model ID is ElevenLabs' own (eleven_multilingual_v2)
  • 29 languages; language takes a base ISO code such as hi (ignored: the language is read from the text)
  • Voice: a premade name or any 20-character ElevenLabs voice ID, including cloned voices
  • Input up to 4096 characters; no SSML
  • Paid plans only

Strengths

  • ElevenLabs' lifelike, consistent-quality model, the most stable on long-form speech
  • 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

Narration, audiobooks and voice-oversCustomer 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_multilingual_v2",
    "voice": "sarah",
    "language": "hi",
    "input": "Namaste, main aapki kaise madad kar sakti hoon?"
  }' --output speech.mp3

Endpoint: POST /v1/audio/speech · Model ID: eleven_multilingual_v2

Try Eleven Multilingual v2 now

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

Start free Book a DemoRead docs