Skip to content
CallMissed
Book a demo

Explore CallMissed

Back to all models
Text to Speechvoice-agentsmultilingualbeta

TTS beta

by Gradium · Released Undisclosed

Gradium's newest text-to-speech model, in beta. English, French, German, Spanish and Portuguese. 13 voices. Voice sessions only. $0.50 per 10K characters.

Text to Speech

TTS beta

Powered by Gradium · Streaming neural TTS (Gradium)

Context Window

N/A

Parameters

Undisclosed

Max Output

N/A

Category

Text to Speech

Overview

Gradium TTS is Gradium's newest text-to-speech model, currently in beta. On CallMissed it runs inside voice agents and voice sessions only, in five languages: English, French, German, Spanish and Portuguese. It has no Indian-language support.

There are 13 voices across American, British and Irish English accents, each with a short description. The default is harper, a modern, confident and friendly American voice. Expressiveness (temperature) is adjustable per agent.

It takes plain text, with no SSML or inline sound tags. POST /v1/audio/speech returns an error for it.

Pricing

MetricPrice
Price /10K chars₹48.0000

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

Key Highlights

  • English, French, German, Spanish and Portuguese
  • 13 voices; default harper
  • American, British and Irish English accents
  • Voice sessions only — not available on the speech endpoint

Benchmarks

BenchmarkScore
Languages5
Voices13
Price$0.50
DeploymentVoice sessions only

Technical Details

  • Languages: en, fr, de, es, pt
  • 13 voices with gender, accent and description from GET /api/v1/models?category=tts
  • Expressiveness (temperature) adjustable per agent
  • Plain text only — no SSML or inline sound tags
  • Voice sessions only — POST /v1/audio/speech returns 400 for this model

Strengths

  • Wide choice of English accents including Irish
  • Voice descriptions available from the API

Limitations

  • Beta model — behaviour may change
  • No Indian languages — use rime-coda or inworld-tts-2 for Hindi
  • Voice sessions only — not available on the speech endpoint

Use Cases

English and European-language voice agentsCustomer support lines outside India

API Example

curl https://api.callmissed.com/v1/voice/sessions \
  -H "Authorization: Bearer cm_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "tts_model": "gradium-tts-beta",
    "voice": "harper",
    "language": "en"
  }'

Endpoint: POST /v1/voice/sessions (voice sessions only) · Model ID: gradium-tts-beta

Try TTS beta now

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

Start free Book a DemoRead docs