All models

Inworld TTS 2

inworld/tts-2
Inworld TTSSpeech SynthesisLow LatencyMultilingualNatural Language SteeringExpressive

Inworld's most powerful and expressive text-to-speech model. Builds on TTS 1.5 with rich expressive speech, real-time latency, natural language steering (e.g. [whisper], [say excitedly]), and stronger multilingual support across 15 production languages plus 90+ experimental languages.

Quick start

# Inspect the price — a plain request returns the 402 challenge:
curl -i https://api.glianalabs.com/v1/infer \
  -H "content-type: application/json" \
  -d '{
    "model": "inworld/tts-2",
    "text": "<text to speak>"
  }'

# Pay + run in one step with the mppx CLI (create a wallet: npx mppx account create):
npx mppx https://api.glianalabs.com/v1/infer \
  -J '{"model": "inworld/tts-2", "text": "<text to speak>"}'

Examples

Parameters

Input
text string required

The text to be synthesized into speech. Maximum input of 2,000 characters.

apply_text_normalization boolean optional

When enabled, text normalization expands numbers, dates, times, and abbreviations before converting to speech. Turning this off may reduce latency.

bit_rate integer optional

Bits per second of the audio. Only for compressed audio formats (mp3, opus). The default is 128,000.

output_format string optional default: "mp3"

The output format for the audio. Supported formats are mp3, opus, wav, and flac. Defaults to mp3.

sample_rate integer optional

The synthesis sample rate in hertz. Accepts: 8000, 16000, 22050, 24000, 32000, 44100, 48000. The default is 48,000.

speaking_rate number optional

Speaking rate/speed, in the range [0.5, 1.5]. The default is 1.0. We recommend using values above 0.8 to ensure high quality.

temperature number optional default: 1

Determines the degree of randomness when sampling audio tokens. Defaults to 1.0. Accepts values between 0 (exclusive) and 2 (inclusive). Higher values = more expressive, lower values = more deterministic.

timestamp_type string optional default: "none"

Controls timestamp metadata returned with the audio. "word" returns word-level timing, "character" returns character-level timing. Note: adds latency. Defaults to none.

voice_id string optional default: "Dennis"

The ID of the voice to use for synthesizing speech. Defaults to Dennis.

Output
audio: URL to the generated audio file