# gemini-3-1-flash-tts

> Gemini 3.1 Flash TTS turns written dialogue into expressive, natural multi-speaker speech with fine-grained control over voice, accent, emotional style, and pace. Ideal for fast, affordable voiceovers, character dialogue, and narration.

## Overview

- **Endpoint**: `POST https://api.muapi.ai/api/v1/gemini-3-1-flash-tts`
- **Model ID**: `gemini-3-1-flash-tts`
- **Category**: text to audio
- **Variant**: 3.1 Flash
- **Family**: gemini-tts
- **Cost**: 0.035 credits per call (some models compute cost dynamically based on params)

## API Usage

MuApi uses a **submit-then-poll** pattern: submit a job, get a `request_id`, then poll the predictions endpoint until `status` is `completed`. Optionally pass `?webhook=YOUR_URL` on the submit call to receive a POST callback when the job finishes (skip polling).

**Authentication**: send your MuApi key in the `x-api-key` header. Get one at https://muapi.ai/access-keys.

### 1. Submit a job

```http
POST https://api.muapi.ai/api/v1/gemini-3-1-flash-tts
Content-Type: application/json
x-api-key: YOUR_API_KEY
```

**Minimum (required only):**

```json
{
  "speakers": [
    {
      "pace": "Natural",
      "style": "Deadpan",
      "accent": "British (RP)",
      "speaker_id": "Speaker 1",
      "voice_name": "Fenrir",
      "audio_profile": "A stern and weary gatekeeper"
    },
    {
      "pace": "Staccato",
      "style": "Empathetic",
      "accent": "American (Gen)",
      "speaker_id": "Speaker 2",
      "voice_name": "Puck",
      "audio_profile": "A determined and courageous traveler seeking answers."
    }
  ],
  "dialogue_turns": [
    {
      "text": "[shouting] Halt, traveler! The northern pass is sealed by order of the council.",
      "speaker_id": "Speaker 1"
    },
    {
      "text": "[determination] I carry a message for the elder. Step aside, or I will force my way through.",
      "speaker_id": "Speaker 2"
    },
    {
      "text": "[caution] No one passes. [pensive] The elder is... he's no longer receiving visitors.",
      "speaker_id": "Speaker 1"
    },
    {
      "text": "It's too late. [whispers] The shadow... it reached him first. [urgency] You need to leave. [shouting] Now.",
      "speaker_id": "Speaker 2"
    }
  ]
}
```

**Full example (all params):**

```json
{
  "scene": "",
  "speakers": [
    {
      "pace": "Natural",
      "style": "Deadpan",
      "accent": "British (RP)",
      "speaker_id": "Speaker 1",
      "voice_name": "Fenrir",
      "audio_profile": "A stern and weary gatekeeper"
    },
    {
      "pace": "Staccato",
      "style": "Empathetic",
      "accent": "American (Gen)",
      "speaker_id": "Speaker 2",
      "voice_name": "Puck",
      "audio_profile": "A determined and courageous traveler seeking answers."
    }
  ],
  "temperature": 1,
  "dialogue_turns": [
    {
      "text": "[shouting] Halt, traveler! The northern pass is sealed by order of the council.",
      "speaker_id": "Speaker 1"
    },
    {
      "text": "[determination] I carry a message for the elder. Step aside, or I will force my way through.",
      "speaker_id": "Speaker 2"
    },
    {
      "text": "[caution] No one passes. [pensive] The elder is... he's no longer receiving visitors.",
      "speaker_id": "Speaker 1"
    },
    {
      "text": "It's too late. [whispers] The shadow... it reached him first. [urgency] You need to leave. [shouting] Now.",
      "speaker_id": "Speaker 2"
    }
  ],
  "sample_context": ""
}
```

**Response:**

```json
{
  "request_id": "abc123",
  "status": "processing"
}
```

### 2. Poll for the result

```http
GET https://api.muapi.ai/api/v1/predictions/{request_id}/result
x-api-key: YOUR_API_KEY
```

Possible `status` values: `queued`, `pending`, `processing`, `completed`, `failed`, `cancelled`. Poll every 2-5 seconds until terminal. When `completed`, the result URLs are in the `outputs` array.

**Example response when `completed`:**

```json
{
  "id": "abc123",
  "status": "completed",
  "outputs": [
    "https://cdn.muapi.ai/.../output.png"
  ],
  "urls": {
    "get": "https://api.muapi.ai/api/v1/predictions/abc123/result"
  },
  "created_at": "2026-05-08T12:34:56Z",
  "has_nsfw_contents": []
}
```

### cURL

```bash
# 1. Submit
REQUEST_ID=$(curl -s -X POST https://api.muapi.ai/api/v1/gemini-3-1-flash-tts \
  -H "x-api-key: $MUAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"speakers":[{"pace":"Natural","style":"Deadpan","accent":"British (RP)","speaker_id":"Speaker 1","voice_name":"Fenrir","audio_profile":"A stern and weary gatekeeper"},{"pace":"Staccato","style":"Empathetic","accent":"American (Gen)","speaker_id":"Speaker 2","voice_name":"Puck","audio_profile":"A determined and courageous traveler seeking answers."}],"dialogue_turns":[{"text":"[shouting] Halt, traveler! The northern pass is sealed by order of the council.","speaker_id":"Speaker 1"},{"text":"[determination] I carry a message for the elder. Step aside, or I will force my way through.","speaker_id":"Speaker 2"},{"text":"[caution] No one passes. [pensive] The elder is... he's no longer receiving visitors.","speaker_id":"Speaker 1"},{"text":"It's too late. [whispers] The shadow... it reached him first. [urgency] You need to leave. [shouting] Now.","speaker_id":"Speaker 2"}]}' | jq -r .request_id)

# 2. Poll until completed
while :; do
  RESP=$(curl -s https://api.muapi.ai/api/v1/predictions/$REQUEST_ID/result -H "x-api-key: $MUAPI_API_KEY")
  STATUS=$(echo "$RESP" | jq -r .status)
  [ "$STATUS" = "completed" ] && echo "$RESP" | jq .outputs && break
  [ "$STATUS" = "failed" ] && echo "$RESP" && exit 1
  sleep 3
done
```

### Python

```python
import os, time, requests

API = "https://api.muapi.ai/api/v1"
headers = {"x-api-key": os.environ["MUAPI_API_KEY"]}

r = requests.post(f"{API}/gemini-3-1-flash-tts", headers=headers, json={"speakers":[{"pace":"Natural","style":"Deadpan","accent":"British (RP)","speaker_id":"Speaker 1","voice_name":"Fenrir","audio_profile":"A stern and weary gatekeeper"},{"pace":"Staccato","style":"Empathetic","accent":"American (Gen)","speaker_id":"Speaker 2","voice_name":"Puck","audio_profile":"A determined and courageous traveler seeking answers."}],"dialogue_turns":[{"text":"[shouting] Halt, traveler! The northern pass is sealed by order of the council.","speaker_id":"Speaker 1"},{"text":"[determination] I carry a message for the elder. Step aside, or I will force my way through.","speaker_id":"Speaker 2"},{"text":"[caution] No one passes. [pensive] The elder is... he's no longer receiving visitors.","speaker_id":"Speaker 1"},{"text":"It's too late. [whispers] The shadow... it reached him first. [urgency] You need to leave. [shouting] Now.","speaker_id":"Speaker 2"}]})
request_id = r.json()["request_id"]

while True:
    res = requests.get(f"{API}/predictions/{request_id}/result", headers=headers).json()
    if res["status"] == "completed":
        print(res["outputs"]); break
    if res["status"] == "failed":
        raise RuntimeError(res.get("error")); 
    time.sleep(3)
```

## Input Schema

The API accepts the following input parameters:

- **`scene`** (`string`, _optional_):
  Optional scene description that sets the acoustic setting, e.g. "A quiet, warm room with a fireplace crackling softly."
  - Default: `""`

- **`speakers`** (`array`, _required_):
  List of speaker voice configurations. Each dialogue turn references a speaker by its ID.
  - **`speakers[].pace`** (`string`, _required_): Speaking pace.
    - Default: `"Natural"`
    - Options: `"Natural"`, `"Rapid Fire"`, `"The Drift"`, `"Staccato"`
  - **`speakers[].style`** (`string`, _required_): Emotional delivery style.
    - Default: `"Empathetic"`
    - Options: `"Vocal Smile"`, `"Newscaster"`, `"Whisper"`, `"Empathetic"`, `"Promo/Hype"`, `"Deadpan"`
  - **`speakers[].accent`** (`string`, _required_): Speaking accent.
    - Default: `"Neutral"`
    - Options: `"Neutral"`, `"American (Gen)"`, `"American (Valley)"`, `"American (South)"`, `"British (RP)"`, `"British (Brixton)"`, `"Transatlantic"`, `"Australian"`
  - **`speakers[].speaker_id`** (`string`, _required_): Speaker identifier. Must be in "Speaker N" format (e.g. "Speaker 1").
  - **`speakers[].voice_name`** (`string`, _required_): Prebuilt Gemini voice name.
    - Options: `"Achernar"`, `"Achird"`, `"Algenib"`, `"Algieba"`, `"Alnilam"`, `"Aoede"`, `"Autonoe"`, `"Callirrhoe"`, `"Charon"`, `"Despina"`, `"Enceladus"`, `"Erinome"`, `"Fenrir"`, `"Gacrux"`, `"Iapetus"`, `"Kore"`, `"Laomedeia"`, `"Leda"`, `"Orus"`, `"Puck"`, `"Pulcherrima"`, `"Rasalgethi"`, `"Sadachbia"`, `"Sadaltager"`, `"Schedar"`, `"Sulafat"`, `"Umbriel"`, `"Vindemiatrix"`, `"Zephyr"`, `"Zubenelgenubi"`
  - **`speakers[].audio_profile`** (`string`, _optional_): Optional natural-language description of the persona, e.g. "A warm and soothing narrator".

- **`temperature`** (`number`, _optional_):
  Sampling temperature (0-2). Higher values produce more varied delivery.
  - Default: `1`
  - Range: `0` to `2`

- **`dialogue_turns`** (`array`, _required_):
  Ordered list of dialogue lines. Each turn's speaker_id must match a speaker defined above. Text may include tone tags like [shouting] or [whispers].
  - **`dialogue_turns[].text`** (`string`, _required_): The line to speak. Supports inline tone tags. Max 10000 characters.
  - **`dialogue_turns[].speaker_id`** (`string`, _required_): ID of the speaker delivering this line (e.g. "Speaker 1").

- **`sample_context`** (`string`, _optional_):
  Optional overall tone/style, e.g. "Audiobook style narration. Tone is gentle and inviting."
  - Default: `""`

## Output Schema

The polling endpoint returns the following fields:

- **`id`** (`string`): The request ID.
- **`status`** (`string`): One of `queued`, `pending`, `processing`, `completed`, `failed`, `cancelled`.
- **`outputs`** (`array`): URLs to generated images/videos/audio. Empty until `status` is `completed`.
- **`urls.get`** (`string`): Self-link to re-fetch this prediction.
- **`error`** (`string` | `null`): Error message if `status` is `failed`.
- **`created_at`** (`string`): ISO-8601 timestamp of when the request was created.
- **`has_nsfw_contents`** (`array of boolean`): Per-output NSFW detection flags.

## Webhooks (optional)

Append `?webhook=https://your-server/path` to the submit URL. When the job reaches a terminal state, MuApi will POST the same shape as the polling response to your URL — no polling needed.

## Agent Integration

MuApi ships an MCP server and CLI so agents (Claude Code, Cursor, custom) can call this endpoint without writing HTTP code:

```bash
# Install the CLI
npm install -g muapi-cli

# Authenticate once
muapi auth login

# Expose all MuApi models as MCP tools to your agent
muapi mcp serve
```

The MCP server exposes tools that wrap submit + poll for every model, including `gemini-3-1-flash-tts`. See `muapi --help` for category-specific shortcuts (`muapi image generate`, `muapi video from-image`, etc.).

## Related Models
- [3.1 Flash](https://muapi.ai/playground/gemini-3-1-flash-tts)
- [2.5 Pro](https://muapi.ai/playground/gemini-2-5-pro-tts)

## Resources
- [Playground Page](https://muapi.ai/playground/gemini-3-1-flash-tts)
- [API Reference](https://muapi.ai/playground/gemini-3-1-flash-tts?tab=2)
- [Global llms.txt](https://muapi.ai/llms.txt)