TTS-2 Flash
by Inworld · Released Undisclosed
The faster, lower-cost Inworld TTS-2. Same 14 voices and 94 languages including 11 Indian languages. Voice sessions only. $0.1563 per 10K characters.
TTS-2 Flash
Powered by Inworld · Streaming neural TTS (Inworld TTS-2 Flash)
Context Window
N/A
Parameters
Undisclosed
Max Output
N/A
Category
Text to Speech
Overview
TTS-2 Flash is the faster, lower-cost variant of Inworld's TTS-2. It has the same 14 voices and the same 94 languages, including Hindi, Marathi, Bengali, Tamil, Telugu, Gujarati, Kannada, Malayalam, Punjabi, Urdu and Odia. On CallMissed it runs inside voice agents and voice sessions only.
The default voice is riya. Speaking rate and expressiveness (temperature) are adjustable per agent.
It performs non-verbal sounds (laugh, sigh, breathe, clear throat, cough) and SSML pauses, but ignores delivery directions. POST /v1/audio/speech returns an error for it. Choose inworld-tts-2 when you want the full model at a slightly higher price.
Pricing
| Metric | Price |
|---|---|
| Price /10K chars | ₹15.0000 |
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
- Faster, lower-cost TTS-2 with the same voices and languages
- 94 languages including 11 Indian languages
- 14 voices; default riya
- Voice sessions only — not available on the speech endpoint
Benchmarks
| Benchmark | Score |
|---|---|
| Languages | 94 |
| Voices | 14 |
| Price | $0.1563 |
| Deployment | Voice sessions only |
Technical Details
- 94 base language codes; every voice speaks every code
- 14 voices; gender and description are listed only where Inworld publishes them
- Speaking rate and expressiveness adjustable per agent
- Non-verbal sounds and SSML pauses; no delivery directions
- Voice sessions only — POST /v1/audio/speech returns 400 for this model
Strengths
- Among the lowest-priced voice-session TTS models
- 94 languages including 11 Indian languages
- Same voices as inworld-tts-2
Limitations
- Voice descriptions and gender are missing for some voices
- Voice sessions only — not available on the speech endpoint
Use Cases
API Example
curl https://api.callmissed.com/v1/voice/sessions \
-H "Authorization: Bearer cm_YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{
"tts_model": "inworld-tts-2-flash",
"voice": "riya",
"language": "hi"
}'Endpoint: POST /v1/voice/sessions (voice sessions only) · Model ID: inworld-tts-2-flash
Try TTS-2 Flash now
Get 1000 free API credits on signup. No credit card required.