Type
Spec
Rate
Input
per 1M prompt tokens
$2.60
Output
per 1M generated tokens
$46.80
Gemini 3.8 Flash TTS and StepAudio 3 TTS side by side: specs, capabilities, parameters, and live pricing from the EmpirioLabs catalog.
Google 
StepFun Audio GenerationGemini 3.8 Flash TTS from Google and StepAudio 3 TTS from StepFun are both in the Audio Generation category, available through the EmpirioLabs API.
| Spec | Gemini 3.8 Flash TTS | StepAudio 3 TTS |
|---|---|---|
| Model ID | gemini-3-8-flash-tts | stepaudio-3-tts |
| Author | StepFun | |
| Released | Sep 22, 2026 | Sep 9, 2026 |
| Input | Text | Text |
| Output | Audio | Audio |
| Region | - | International |
| Endpoints | POST /v1/audio/speech POST /v1/audio/speech:stream GET /v1/voices | POST /v1/audio/speech POST /v1/audio/speech:stream |
| 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 | Gemini 3.8 Flash TTS | StepAudio 3 TTS |
|---|---|---|
| input | max 5000 | max 1000 |
| mode | single, multi Default: single | - |
| language | string | en, zh, ja, ko, fr, es Default: en |
| voice | Zephyr, Puck, Charon, Kore, Fenrir, Leda, Orus, Aoede, Callir... Default: Charon | lively-girl, vibrant-youth, soft-spoken-gentleman, magnetic-v... Default: lively-girl |
| voice_audio_url | string | - |
| voice_consent_audio_url | string | - |
| voice2 | Zephyr, Puck, Charon, Kore, Fenrir, Leda, Orus, Aoede, Callir... Default: Kore | - |
| speaker1_name | string Default: Speaker1 | - |
| speaker2_name | string Default: Speaker2 | - |
| output_format | WAV, MP3, OGG, ALAW, MULAW Default: WAV | - |
| speed | 0.25 to 2 Default: 1 | 0.5 to 2 Default: 1 |
| volume_gain | -96 to 16 Default: 0 | - |
| sample_rate | 8000, 16000, 22050, 24000, 44100, 48000 Default: 24000 | 8000, 16000, 22050, 24000 Default: 24000 |
| style_prompt | string | - |
| instruction | - | max 500 |
| volume | - | 0.1 to 2 Default: 1 |
<argh> <breath> <heavy breath> <exhales> <cackle> <cheer> <chuckle> <chuckles> <cough> <cry> <gasp> <giggle> <groan> <growl> <grunt> <grr> <hiss> <laugh> <laughter> <moan> <pant> <pff> <phew> <scream> <shout> <shriek> <sigh> <sighs> <sneeze> <snicker> <snort> <sob> <throat-clearing> <tsk> <whimper> <whispers> <whispering> <yawn> <short pause> <long pause>Maximum input is 1,000 characters. Content in parentheses is treated as delivery direction and is not spoken. Use instruction for global emotion or style guidance, up to 500 characters. Twelve system voices are available. Recognized languages are Chinese, English, Japanese, Korean, French, and Spanish, with languages other than Chinese and English in preview. Output formats are mp3, wav, flac, opus, and pcm at 8000, 16000, 22050, or 24000 Hz. Wav is returned as a complete file rather than streamed. This model does not support voice_label.
Gemini 3.8 Flash TTS serves speech through POST /v1/audio/speech and returns playable audio. Send the text to speak as input with the model id gemini-3-8-flash-tts. Both models are called through the same endpoint. Set model to gemini-3-8-flash-tts or stepaudio-3-tts. 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": "gemini-3-8-flash-tts",
"input": "Welcome to EmpirioLabs. Your build just finished."
}' \
--output speech.mp3Prompt tests and comparison runs that cover both models.
Gemini 3.8 Flash TTS is the newer release (Sep 22, 2026); StepAudio 3 TTS was released on Sep 9, 2026. Capabilities listed only for Gemini 3.8 Flash TTS: multi speaker, voice tags, streaming, voice cloning. Capabilities listed only for StepAudio 3 TTS: contextual tts. The specs, rate cards, and parameters on this page come from the live EmpirioLabs catalog.
Gemini 3.8 Flash TTS is the newer release (Sep 22, 2026); StepAudio 3 TTS was released on Sep 9, 2026.
The two models are priced on different units or tiers, so compare the live rate cards on this page. They 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.
