TTS 2 Flash Save up to 30%tts-2-flash
Type
Spec
Rate
Synthesis
per 1M characters
$15.00$10.50
TTS 2 Flash and TTS 2 side by side: specs, capabilities, parameters, and live pricing from the EmpirioLabs catalog.
Inworld Audio GenerationTTS 2 Flash and TTS 2 are both Inworld models in the Audio Generation category, available through the EmpirioLabs API.
| Spec | TTS 2 Flash | TTS 2 |
|---|---|---|
| Model ID | tts-2-flash | tts-2 |
| Author | Inworld | Inworld |
| Released | Sep 2, 2026 | May 5, 2026 |
| Input | Text | Text |
| Output | Audio | Audio |
| Endpoints | POST /v1/audio/speech POST /v1/audio/speech:stream GET /v1/voices | POST /v1/audio/speech POST /v1/audio/speech:stream GET /v1/voices |
| Capabilities |
Live rates from the EmpirioLabs catalog for both models. Each rate card always matches what the API charges.
Request parameters each model lists on EmpirioLabs, with the allowed values or range where one applies. A dash marks a parameter the model does not list.
| Parameter | TTS 2 Flash | TTS 2 |
|---|---|---|
| input | max 2000 | max 2000 |
| voice | Sarah, Olivia, Elizabeth, Ashley, Wendy, Julia, Priya, Pixie,... Default: Sarah | Sarah, Olivia, Elizabeth, Ashley, Wendy, Julia, Priya, Pixie,... Default: Sarah |
| voice_id | string | string |
| language | en-US, en-GB, es-ES, es-MX, fr-FR, de-DE, it-IT, pt-BR, pt-PT... Default: en-US | en-US, en-GB, es-ES, es-MX, fr-FR, de-DE, it-IT, pt-BR, pt-PT... Default: en-US |
| output_format | MP3, WAV, OGG, FLAC, PCM, ALAW, MULAW Default: WAV | MP3, WAV, OGG, FLAC, PCM, ALAW, MULAW Default: WAV |
| sample_rate | 8000, 16000, 22050, 24000, 32000, 44100, 48000 Default: 24000 | 8000, 16000, 22050, 24000, 32000, 44100, 48000 Default: 24000 |
| speed | 0.5 to 1.5 Default: 1 | 0.5 to 1.5 Default: 1 |
| temperature | 0.1 to 2 Default: 1 | 0.1 to 2 Default: 1 |
| bit_rate | 32000 to 320000 Default: 128000 | 32000 to 320000 Default: 128000 |
| apply_text_normalization | ON, OFF Default: ON | ON, OFF Default: ON |
| timestamp_type | NONE, WORD, CHARACTER Default: NONE | NONE, WORD, CHARACTER Default: NONE |
TTS 2 Flash serves speech through POST /v1/audio/speech and returns playable audio. Send the text to speak as input with the model id tts-2-flash. Both models are called through the same endpoint. Set model to tts-2-flash or tts-2. Get an API key from the EmpirioLabs dashboard.
curl https://api.empiriolabs.ai/v1/audio/speech \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "tts-2-flash",
"input": "Welcome to EmpirioLabs. Your build just finished."
}' \
--output speech.mp3TTS 2 Flash is the newer release (Sep 2, 2026); TTS 2 was released on May 5, 2026. Capabilities listed only for TTS 2: expressive prosody, voice direction. TTS 2 Flash lists the lower rate for Synthesis (per 1M characters). The specs, rate cards, and parameters on this page come from the live EmpirioLabs catalog.
TTS 2 Flash is the newer release (Sep 2, 2026); TTS 2 was released on May 5, 2026.
TTS 2 Flash lists the lower rate for Synthesis (per 1M characters). Both live rate cards are on this page and always match what the API charges.
Yes. Both models use POST /v1/audio/speech with the same EmpirioLabs API key, so most integrations switch by changing the model value. Check the parameters table on this page first if you rely on a model-specific parameter.
Yes. Open each model in the EmpirioLabs playground and run the same prompt on both, with the parameters the API exposes.
Check out our pricing or reach out if you want your own model deployed on our stack.