> ## Documentation Index
> Fetch the complete documentation index at: https://veniceai-docs-responses-api.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Text-to-Speech-Modelle

> Venice-Text-to-Speech-Modelle wie Kokoro, ElevenLabs Turbo und Orpheus mit mehrsprachigen Stimmen, Preisen pro Zeichen und Streaming-Audio.

<div id="model-search-placeholder" data-filter="tts">
  Verwenden Sie den `id`-Wert als `model`-Parameter in API-Anfragen. Derzeit sind 11 Modelle verfügbar.

  | Model | ID | Pro 1M Zeichen | Stimmen | Privacy |
  | - | - | - | - | - |
  | Chatterbox HD (Resemble AI) | `tts-chatterbox-hd` | \$50.00 | 9 | Private |
  | ElevenLabs Turbo v2.5 | `tts-elevenlabs-turbo-v2-5` | \$62.50 | 21 | Anonymized |
  | Gemini 3.1 Flash TTS | `tts-gemini-3-1-flash` | \$187.50 | 30 | Anonymized |
  | Gradium TTS | `tts-gradium-v1` | \$47.50 | 12 | Anonymized |
  | Inworld TTS-1.5 Max | `tts-inworld-1-5-max` | \$12.50 | 14 | Anonymized |
  | Kokoro Text to Speech | `tts-kokoro` | \$3.50 | 54 | Private |
  | MiniMax Speech-02 HD | `tts-minimax-speech-02-hd` | \$125.00 | 15 | Anonymized |
  | Orpheus TTS | `tts-orpheus` | \$62.50 | 8 | Private |
  | Qwen 3 TTS 0.6B | `tts-qwen3-0-6b` | \$87.50 | 9 | Private |
  | Qwen 3 TTS 1.7B | `tts-qwen3-1-7b` | \$112.50 | 9 | Private |
  | xAI TTS v1 | `tts-xai-v1` | \$18.75 | 26 | Anonymized |
</div>

***

## Stimmkatalog

Stimmen sind **modellspezifisch**. Die `voice`, die Sie übergeben, muss aus dem
Katalog des gewählten `model` stammen. Wählen Sie unten ein Modell, um dessen Stimmen zu durchsuchen.

<div id="tts-voice-picker-placeholder">
  #### Chatterbox HD (Resemble AI) (`tts-chatterbox-hd`)

  | Voice-ID |
  | - |
  | `Aurora` |
  | `Blade` |
  | `Britney` |
  | `Carl` |
  | `Cliff` |
  | `Richard` |
  | `Rico` |
  | `Siobhan` |
  | `Vicky` |

  #### ElevenLabs Turbo v2.5 (`tts-elevenlabs-turbo-v2-5`)

  | Voice-ID |
  | - |
  | `Alice` |
  | `Aria` |
  | `Bill` |
  | `Brian` |
  | `Callum` |
  | `Charlie` |
  | `Charlotte` |
  | `Chris` |
  | `Daniel` |
  | `Eric` |
  | `George` |
  | `Jessica` |
  | `Laura` |
  | `Liam` |
  | `Lily` |
  | `Matilda` |
  | `Rachel` |
  | `River` |
  | `Roger` |
  | `Sarah` |
  | `Will` |

  #### Gemini 3.1 Flash TTS (`tts-gemini-3-1-flash`)

  | Voice-ID |
  | - |
  | `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` |

  #### Gradium TTS (`tts-gradium-v1`)

  | Voice-ID |
  | - |
  | `Alice` |
  | `Davi` |
  | `Elise` |
  | `Emma` |
  | `Eva` |
  | `Jack` |
  | `Kent` |
  | `Leo` |
  | `Maximilian` |
  | `Mia` |
  | `Sergio` |
  | `Valentina` |

  #### Inworld TTS-1.5 Max (`tts-inworld-1-5-max`)

  | Voice-ID |
  | - |
  | `Alex` |
  | `Ashley` |
  | `Craig` |
  | `Edward` |
  | `Elizabeth` |
  | `Hades` |
  | `Luna` |
  | `Mark` |
  | `Olivia` |
  | `Pixie` |
  | `Priya` |
  | `Ronald` |
  | `Sarah` |
  | `Theodore` |

  #### Kokoro Text to Speech (`tts-kokoro`)

  | Voice-ID |
  | - |
  | `af_alloy` |
  | `af_aoede` |
  | `af_bella` |
  | `af_heart` |
  | `af_jadzia` |
  | `af_jessica` |
  | `af_kore` |
  | `af_nicole` |
  | `af_nova` |
  | `af_river` |
  | `af_sarah` |
  | `af_sky` |
  | `am_adam` |
  | `am_echo` |
  | `am_eric` |
  | `am_fenrir` |
  | `am_liam` |
  | `am_michael` |
  | `am_onyx` |
  | `am_puck` |
  | `am_santa` |
  | `bf_alice` |
  | `bf_emma` |
  | `bf_lily` |
  | `bm_daniel` |
  | `bm_fable` |
  | `bm_george` |
  | `bm_lewis` |
  | `ef_dora` |
  | `em_alex` |
  | `em_santa` |
  | `ff_siwis` |
  | `hf_alpha` |
  | `hf_beta` |
  | `hm_omega` |
  | `hm_psi` |
  | `if_sara` |
  | `im_nicola` |
  | `jf_alpha` |
  | `jf_gongitsune` |
  | `jf_nezumi` |
  | `jf_tebukuro` |
  | `jm_kumo` |
  | `pf_dora` |
  | `pm_alex` |
  | `pm_santa` |
  | `zf_xiaobei` |
  | `zf_xiaoni` |
  | `zf_xiaoxiao` |
  | `zf_xiaoyi` |
  | `zm_yunjian` |
  | `zm_yunxi` |
  | `zm_yunxia` |
  | `zm_yunyang` |

  #### MiniMax Speech-02 HD (`tts-minimax-speech-02-hd`)

  | Voice-ID |
  | - |
  | `CalmWoman` |
  | `CasualGuy` |
  | `DeepVoiceMan` |
  | `DeterminedMan` |
  | `ElegantMan` |
  | `ExuberantGirl` |
  | `FriendlyPerson` |
  | `ImposingManner` |
  | `InspirationalGirl` |
  | `LivelyGirl` |
  | `LovelyGirl` |
  | `PatientMan` |
  | `SweetGirl` |
  | `WiseWoman` |
  | `YoungKnight` |

  #### Orpheus TTS (`tts-orpheus`)

  | Voice-ID |
  | - |
  | `dan` |
  | `jess` |
  | `leah` |
  | `leo` |
  | `mia` |
  | `tara` |
  | `zac` |
  | `zoe` |

  #### Qwen 3 TTS 0.6B (`tts-qwen3-0-6b`)

  | Voice-ID |
  | - |
  | `Aiden` |
  | `Dylan` |
  | `Eric` |
  | `Ono_Anna` |
  | `Ryan` |
  | `Serena` |
  | `Sohee` |
  | `Uncle_Fu` |
  | `Vivian` |

  #### Qwen 3 TTS 1.7B (`tts-qwen3-1-7b`)

  | Voice-ID |
  | - |
  | `Aiden` |
  | `Dylan` |
  | `Eric` |
  | `Ono_Anna` |
  | `Ryan` |
  | `Serena` |
  | `Sohee` |
  | `Uncle_Fu` |
  | `Vivian` |

  #### xAI TTS v1 (`tts-xai-v1`)

  | Voice-ID |
  | - |
  | `altair` |
  | `ara` |
  | `atlas` |
  | `carina` |
  | `castor` |
  | `celeste` |
  | `cosmo` |
  | `eve` |
  | `helios` |
  | `helix` |
  | `iris` |
  | `kepler` |
  | `leo` |
  | `lumen` |
  | `luna` |
  | `lux` |
  | `naksh` |
  | `orion` |
  | `perseus` |
  | `rex` |
  | `rigel` |
  | `sal` |
  | `sirius` |
  | `ursa` |
  | `zagan` |
  | `zenith` |
</div>

<Note>
  Voice-IDs sind case-sensitiv und **nur für das passende `model` gültig**. Übergeben Sie
  beide Felder zusammen in Ihrem Request-Payload. Beispiele finden Sie in der
  [Audio-Speech-API](/de/api-reference/endpoint/audio/speech).
</Note>

### Beispielanfrage

```bash theme={null}
curl https://api.venice.ai/api/v1/audio/speech \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tts-kokoro",
    "voice": "af_sky",
    "input": "Hello from Venice."
  }' \
  --output speech.mp3
```

Um Modelle zu wechseln, ändern Sie **beide**: `model` und `voice` zu einem Paar aus dem
oben gewählten Modell.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.