Skip to content
CallMissed
Book a demo

Explore CallMissed

Back to all models
Text to Speechvoice-agentsexpressivemultilingual

Drama 3

by Fish Audio · Released Undisclosed

Fish Audio's newest expressive text-to-speech model. 13 languages, no Indian languages. 7 voices. Voice sessions only. $0.5208 per 10K characters.

Text to Speech

Drama 3

Powered by Fish Audio · Streaming neural TTS (Fish Audio Drama)

Context Window

N/A

Parameters

Undisclosed

Max Output

N/A

Category

Text to Speech

Overview

Drama 3 is Fish Audio's newest expressive text-to-speech model. On CallMissed it runs inside voice agents and voice sessions only, in 13 languages: English, Chinese, Japanese, German, French, Spanish, Korean, Arabic, Russian, Dutch, Italian, Polish and Portuguese. It has no Indian-language support.

There are 7 voices, the default being selene, a meditative voice. Only the voices on our list are available; custom Fish Audio voices are not. Speaking speed and expressiveness (temperature) are adjustable per agent.

It performs delivery directions and non-verbal sounds (laughing, chuckling, sighing), but not SSML. It reads the rupee sign as dollars, so voice agents speak amounts and dates in words for it. POST /v1/audio/speech returns an error for it.

Pricing

MetricPrice
Price /10K chars₹50.0000

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

  • Expressive delivery across 13 languages
  • 7 voices; default selene
  • Speed and expressiveness adjustable per agent
  • Voice sessions only — not available on the speech endpoint

Benchmarks

BenchmarkScore
Languages13
Voices7
Price$0.5208
DeploymentVoice sessions only

Technical Details

  • Languages: en, zh, ja, de, fr, es, ko, ar, ru, nl, it, pl, pt
  • 7 voices with description (and gender where published)
  • Custom Fish Audio voices are not available
  • Delivery directions and non-verbal sounds; no SSML
  • Voice sessions only — POST /v1/audio/speech returns 400 for this model

Strengths

  • Expressive, character-rich delivery
  • Speed and temperature controls

Limitations

  • No Indian languages — use rime-coda or inworld-tts-2 for Hindi
  • Only 7 voices
  • Voice sessions only — not available on the speech endpoint

Use Cases

Expressive English voice agentsStorytelling and narration agentsMultilingual agents 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": "fish-audio-drama-3",
    "voice": "selene",
    "language": "en"
  }'

Endpoint: POST /v1/voice/sessions (voice sessions only) · Model ID: fish-audio-drama-3

Try Drama 3 now

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

Start free Book a DemoRead docs