Capabilities
Explore what Inworld TTS-2 supports, then use the API section for a request tailored to this model.
Languages
Model Information
- Provider
- Inworld AI
- Product
- Text-to-Speech
- Release Date
- May 5, 2026
- Data Policy
- Not specified
- Region
- US
- Input
- Text
- Output
- Audio
Playground
Try Inworld TTS-2 by Inworld AI. Requests use the selected workspace’s credits and API pricing.
Providers
Compare available endpoints, pricing, and context limits for Inworld TTS-2.
| Provider | Context | Output | Input Price | Output Price | Endpoint |
|---|---|---|---|---|---|
| Inworld AI | Not specified | Audio | $21.25 / 1M characters | — | inworld/tts-2:inworld |
Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.
Input and Output Limits
Formats and limits AudioLab enforces on each request.
| Limit | Value |
|---|---|
| Max chars | 2000 |
| Formats | mp3, opus, flac, wav, pcm, ulaw, alaw |
Provider Notes
inworld/realtime is AudioLab's provider-managed Inworld STT-1 + GPT-4o + Inworld TTS-2 speech-to-speech stack, with Ashley as the auto voice. All three TTS models support buffered and streaming HTTP audio, native JSON/NDJSON timestamp responses, and a multiplexed speech WebSocket with up to five contexts. TTS-2 is an exact-only preview with bracketed steering, deliveryMode, and 100+ languages; it ignores temperature, so AudioLab rejects that field. Stable TTS 1.5 Max and Mini support temperature and 15 languages but not steering or deliveryMode. AudioLab preserves native alignment, phoneme, viseme, usage, status, and context events.
Performance
Status
Current catalog availability. Your workspace’s access is checked separately before a request runs.
A live availability check is not available right now.
Getting Started
Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.
curl "$AUDIOLAB_API_URL/v1/audio/speech" \
-H "Authorization: Bearer $AUDIOLAB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "inworld/tts-2",
"input": "Make every word count.",
"voice": "auto",
"response_format": "mp3"
}' --output speech.mp3Request Parameters
Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.
| Parameter | Details |
|---|---|
model | inworld/tts-2 — Required model identifier. |
transport | View Accepted Values |
audioConfig | View Accepted Values |
temperature | View Accepted Values |
deliveryMode | View Accepted Values |
timestampType | View Accepted Values |
applyTextNormalization | View Accepted Values |
timestampTransportStrategy | View Accepted Values |
contextId (WebSocket) | View Accepted Values |
maxBufferDelayMs (WebSocket) | View Accepted Values |
bufferCharThreshold (WebSocket) | View Accepted Values |
autoMode (WebSocket) | View Accepted Values |
Input and Output Limits
Formats and limits AudioLab enforces on each request.
| Limit | Value |
|---|---|
| Max chars | 2000 |
| Formats | mp3, opus, flac, wav, pcm, ulaw, alaw |
Similar Models
Explore more text-to-speech and compare their capabilities.
| Model | Context | Input Price | Output Price |
|---|---|---|---|
| Inworld TTS-2 FlashInworld AI | Not specified | $12.75 / 1M characters | — |
| Inworld TTS-1.5 MaxInworld AI | Not specified | $21.25 / 1M characters | — |
| Inworld TTS-1.5 MiniInworld AI | Not specified | $12.75 / 1M characters | — |
| Sonic 3.6Cartesia | Not specified | $38.25 / 1M characters | — |
| Sonic 3.6 (2026-08-27)Cartesia | Not specified | $38.25 / 1M characters | — |
| tts-rt-v2Soniox | Not specified | $11.985 / 1M characters | — |
