Gemini 3.8 Flash Lite TTS via the Tokenator API
What the model is for
Gemini 3.8 Flash Lite TTS is a text-to-speech model from Google and the fast, high-throughput member of the 3.8 TTS family alongside Gemini 3.8 Flash TTS. It is suited for conversational voice-agent pipelines, high-volume read-aloud, and voice replication workloads where latency and cost matter more than maximum expressiveness.
Specification
| Full name | Gemini 3.8 Flash Lite TTS |
| API ID | gemini-3.8-flash-lite-tts |
| Model vendor | Gemini |
| Type | Speech: text to speech (TTS) |
| Context window | 33K tokens |
| Voices | Zephyr, Puck, Charon, Kore, Fenrir, Leda, Orus, Aoede, Callirrhoe, Autonoe, Enceladus, Iapetus, Umbriel, Algieba, Despina, Erinome, Algenib, Rasalgethi, Laomedeia, Achernar, Alnilam, Schedar, Gacrux, Pulcherrima, Achird, Zubenelgenubi, Vindemiatrix, Sadachbia, Sadaltager, Sulafat. |
| Default voice | Zephyr |
| Audio formats | wav, mp3, flac, pcm |
| Default format | mp3 |
| Tokenator usage multiplier | 2.4× |
| Badge | NEW |
| Input modalities | text |
| Supported API formats | /v1/audio/speech |
| Upstream providers | 1 |
| Current status | available |
| Data updated | 2026-11-04 |
Upstream providers
| Provider | Multiplier |
|---|---|
| FastCluster | 2.4× |
A request goes to the first available provider by priority; if it fails, Tokenator switches to the next one.
Example request
curl https://api.tokenator.top/v1/audio/speech \ -H "Authorization: Bearer sk-your-tokenator-key" \ -H "Content-Type: application/json" \ --output speech.mp3 \ -d '{ "input": "Hello!", "model": "gemini-3.8-flash-lite-tts", "response_format": "mp3", "voice": "Zephyr" }'
See also
FAQ about Gemini 3.8 Flash Lite TTS
What is the API ID of Gemini 3.8 Flash Lite TTS?
gemini-3.8-flash-lite-tts — put this into the model field of your request.
How do I call this model?
Send POST /v1/audio/speech with the model's API ID. Request examples and parameters are in the audio documentation.
Why is the model absent from /v1/models?
Audio models have a separate catalog at GET /v1/audio/models. Use ?task=tts for synthesis or ?task=stt for transcription. Chat endpoints refuse audio models.
Which API key should I use?
Use your regular Tokenator key with access to this model. Send it in the Authorization: Bearer sk-your-tokenator-key header.
How do I choose a voice?
Set voice in the JSON request. The catalog's audio_options exposes model capabilities, including voices and default_voice. You can omit voice when a default is configured.
How do I save the synthesized audio?
The response is a binary audio file. Use --output speech.mp3 with curl, or write response.content in wb mode with Python. Select the format with response_format.
Can I adjust speaking speed and style?
The speed and instructions parameters pass upstream. Their effect depends on the selected model. See the audio documentation for parameters and examples.