# Gemini 3.8 Flash TTS

> Generate expressive multi-speaker speech with Gemini 3.8 Flash TTS. Studio-grade voice fidelity and long-form stability. Try free, pay per use.

## Panoramica

- **Endpoint**: `POST https://api.muapi.ai/api/v1/gemini-3-8-flash-tts`
- **ID modello**: `gemini-3-8-flash-tts`
- **Categoria**: Audio AI
- **Variante**: 3.8 Flash
- **Famiglia**: gemini-tts
- **Costo**: 0.015 crediti per chiamata (alcuni modelli calcolano il costo dinamicamente in base ai parametri)

## Utilizzo dell'API

MuApi utilizza un modello **submit-then-poll**: invia un lavoro, ottieni un `request_id`, quindi esegui il polling dell'endpoint delle previsioni finché lo `status` non è `completed`. Facoltativamente, passa `?webhook=YOUR_URL` sulla chiamata di invio per ricevere una richiamata POST al termine del lavoro (salta il polling).

**Autenticazione**: invia la tua chiave MuApi nell'intestazione `x-api-key`. Prendine uno alle https://muapi.ai/access-keys.

### 1. Invia attività

```http
POST https://api.muapi.ai/api/v1/gemini-3-8-flash-tts
Content-Type: application/json
x-api-key: YOUR_API_KEY
```

**Minimo (solo obbligatorio):**

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

**Esempio completo (tutti i parametri):**

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

**Risposta:**

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

### 2. Controlla risultato

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

Possibili valori di "status": "queued", "pending", "processing", "completed", "failed", "cancelled". Sondaggio ogni 2-5 secondi fino al terminale. Una volta "completato", gli URL dei risultati si trovano nell'array "outputs".

**Esempio di risposta al completamento:**

```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. Invia attività
REQUEST_ID=$(curl -s -X POST https://api.muapi.ai/api/v1/gemini-3-8-flash-tts \
  -H "x-api-key: $MUAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"speakers":[{"speaker_id":"Speaker 1","voice_name":"Fenrir","audio_profile":"A stern and weary gatekeeper","accent":"British (RP)","style":"Deadpan","pace":"Natural"},{"speaker_id":"Speaker 2","voice_name":"Puck","audio_profile":"A determined and courageous traveler seeking answers.","accent":"American (Gen)","style":"Empathetic","pace":"Staccato"}],"dialogue_turns":[{"speaker_id":"Speaker 1","text":"[shouting] Halt, traveler! The northern pass is sealed by order of the council."},{"speaker_id":"Speaker 2","text":"[determination] I carry a message for the elder. Step aside, or I will force my way through."},{"speaker_id":"Speaker 1","text":"[caution] No one passes. [pensive] The elder is... he's no longer receiving visitors."},{"speaker_id":"Speaker 2","text":"It's too late. [whispers] The shadow... it reached him first. [urgency] You need to leave. [shouting] Now."}]}' | jq -r .request_id)

2. Controlla fino al completamento
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-3-8-flash-tts", headers=headers, json={"speakers":[{"speaker_id":"Speaker 1","voice_name":"Fenrir","audio_profile":"A stern and weary gatekeeper","accent":"British (RP)","style":"Deadpan","pace":"Natural"},{"speaker_id":"Speaker 2","voice_name":"Puck","audio_profile":"A determined and courageous traveler seeking answers.","accent":"American (Gen)","style":"Empathetic","pace":"Staccato"}],"dialogue_turns":[{"speaker_id":"Speaker 1","text":"[shouting] Halt, traveler! The northern pass is sealed by order of the council."},{"speaker_id":"Speaker 2","text":"[determination] I carry a message for the elder. Step aside, or I will force my way through."},{"speaker_id":"Speaker 1","text":"[caution] No one passes. [pensive] The elder is... he's no longer receiving visitors."},{"speaker_id":"Speaker 2","text":"It's too late. [whispers] The shadow... it reached him first. [urgency] You need to leave. [shouting] Now."}]})
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)
```

## Schema di input

L'API accetta i seguenti parametri di input:

- **`speakers`** (`array`, _required_):
  . ID .
  - **`speakers[].speaker_id`** (`string`, _required_): . "Altoparlante N" ("Altoparlante 1").
  - **`speakers[].voice_name`** (`string`, _required_): Gemelli.
    - Opzioni: `"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".
  - **`speakers[].accent`** (`string`, _required_): .
    - Predefinito: `"Neutral"`
    - Opzioni: `"Neutral"`, `"American (Gen)"`, `"American (Valley)"`, `"American (South)"`, `"British (RP)"`, `"British (Brixton)"`, `"Transatlantic"`, `"Australian"`
  - **`speakers[].style`** (`string`, _required_): .
    - Predefinito: `"Empathetic"`
    - Opzioni: `"Vocal Smile"`, `"Newscaster"`, `"Whisper"`, `"Empathetic"`, `"Promo/Hype"`, `"Deadpan"`
  - **`speakers[].pace`** (`string`, _required_): .
    - Predefinito: `"Natural"`
    - Opzioni: `"Natural"`, `"Rapid Fire"`, `"The Drift"`, `"Staccato"`

- **`dialogue_turns`** (`array`, _required_):
  . id_altoparlante. [gridando] [sussurrando] .
  - **`dialogue_turns[].speaker_id`** (`string`, _required_): ID ("Altoparlante 1") .
  - **`dialogue_turns[].text`** (`string`, _required_): . compatibile con. 10000 .

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

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

- **`temperature`** (`number`, _optional_):
  (0-2) . , .
  - Predefinito: `1`
  - Gamma: `0` to `2`

## Schema di uscita

L'endpoint del polling restituisce i seguenti campi:

- **`id`** (`string`): L'ID della richiesta.
- **`status`** (`string`): Uno tra "in coda", "in sospeso", "in elaborazione", "completato", "non riuscito", "annullato".
- **`outputs`** (`array`): URL alle immagini/video/audio generati. Vuoto finché lo "stato" non è "completato".
- **`urls.get`** (`string`): Collegamento automatico per recuperare questa previsione.
- **`error`** (`string` | `null`): Messaggio di errore se lo "status" è "failed".
- **`created_at`** (`string`): Timestamp ISO-8601 di quando è stata creata la richiesta.
- **`has_nsfw_contents`** (`array of boolean`): Flag di rilevamento NSFW per uscita.

## Webhook (facoltativo)

Aggiungi `?webhook=https://your-server/path` all'URL di invio. Quando il lavoro raggiunge uno stato terminale, MuApi pubblicherà la stessa forma della risposta al polling al tuo URL, senza bisogno di polling.

## Integrazione dell'agente

MuApi fornisce un server MCP e una CLI in modo che gli agenti (Claude Code, Cursor, personalizzato) possano chiamare questo endpoint senza scrivere codice HTTP:

```bash
# Installa la CLI
npm install -g muapi-cli

# Autenticati una volta
muapi auth login

# Esponi tutti i modelli MuApi come strumenti MCP al tuo agente
muapi mcp serve
```

Il server MCP espone strumenti che racchiudono invio e sondaggio per ogni modello, incluso "gemini-3-8-flash-tts". Vedi `muapi --help` per le scorciatoie specifiche della categoria ("muapi image generate`, `muapi video from-image`, ecc.).

## Modelli correlati
- [3.1 Flash](https://muapi.ai/it/playground/gemini-3-1-flash-tts)
- [2.5 Pro](https://muapi.ai/it/playground/gemini-2-5-pro-tts)
- [3.8 Flash Lite](https://muapi.ai/it/playground/gemini-3-8-flash-lite-tts)
- [3.8 Flash](https://muapi.ai/it/playground/gemini-3-8-flash-tts)

## Risorse
- [Pagina del parco giochi](https://muapi.ai/it/playground/gemini-3-8-flash-tts)
- [Riferimento API](https://muapi.ai/it/playground/gemini-3-8-flash-tts/api)
- [Global llms.txt](https://muapi.ai/it/llms.txt)