Gemini-3.1-Flash-TTS | EmpirioLabs AI Docs

Provider: Google
Category: Audio Generation
Endpoint: POST /v1/audio/speech
Context window: —
Served from: —

Highly controllable TTS with new Audio Tags for precise style, tone, pace, and delivery across narration, assistants, and voice apps.

At a glance

Field	Value
Model id	`gemini-3-1-flash-tts`
Input modalities	text
Output modalities	audio
Context window	—
Region	—
Features	—
New	Yes
Native inference	No

Pricing

Charge	Spec	Rate
Input (text)	per 1k tokens	$0.0026
Output (audio)	per 1k tokens	$0.053

Example request

$ curl https://api.empiriolabs.ai/v1/audio/speech \
>   -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
>   -H 'Content-Type: application/json' \
>   -d '{"model": "gemini-3-1-flash-tts", "input": "Hello from EmpirioLabs."}'

Parameters

Parameter	Type	Required	Default	Description
`input`	string	yes	—	Text to synthesize (≤4000 chars). Audio tags supported: [whispers], [laughs], [excited], [sigh], [shouting].
`mode`	enum	no	`"single"`	single: one voice. multi: two-speaker dialog (use [Speaker1]: / [Speaker2]: prefixes in input). · Allowed: `single`, `multi`
`language`	string	no	`"en-US"`	BCP-47 code. 24 GA + 50+ preview supported. Common: en-US, en-IN, ja-JP, ko-KR, fr-FR, de-DE, …
`voice`	enum	no	`"Charon"`	Single mode + first voice for multi mode. 30 distinct Gemini TTS voices, each with a unique timbre. · Allowed: `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`
`voice2`	enum	no	`"Kore"`	Second voice for multi mode. · Allowed: `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`
`speaker1_name`	string	no	`"Speaker1"`	Multi mode label for the first speaker (alphanumeric).
`speaker2_name`	string	no	`"Speaker2"`	Multi mode label for the second speaker (alphanumeric).
`output_format`	enum	no	`"WAV"`	Allowed: `WAV`, `MP3`, `OGG`, `ALAW`, `MULAW`
`speed`	number	no	`1`	Speaking rate multiplier (step 0.25). · Range: 0.25 – 2
`volume_gain`	number	no	`0`	Output gain in dB. · Range: -96 – 16
`sample_rate`	enum	no	`"24000"`	Output sample rate in Hz. · Allowed: `8000`, `16000`, `22050`, `24000`, `44100`, `48000`
`style_prompt`	string	no	—	Free-form style guidance, prepended to input (≤4000 chars). Examples: ‘Read with a calm, professional tone’ or ‘Speak excitedly’.

Live machine-readable schema is also available at GET https://api.empiriolabs.ai/v1/models/gemini-3-1-flash-tts.