Saltar al contenido principal

Text-to-Speech Models

Speech synthesis with multilingual voices, priced per character.

15 families · 15 model IDsUpdated Nov 14, 2026
  • Chatterbox HD is Resemble AI’s open-weight text-to-speech model, known for expressive, natural delivery. It offers 9 voices and returns WAV audio.

    Private · 9 voices
  • Multilingual text-to-speech using ElevenLabs. Supports 29 languages with high-quality natural-sounding voices, configurable speed, and accent accuracy.

    Anonymized · 20 voices
  • ElevenLabs TTS v3$115/ 1M chars

    Generate natural text-to-speech audio using ElevenLabs Eleven-v3. High-quality voices with stability control and automatic text normalization.

    Anonymized · 20 voices
  • ElevenLabs TTS v4$92.00/ 1M chars

    Generate expressive text-to-speech audio using ElevenLabs Eleven-v4. High-quality voices with audio tag support and automatic text normalization.

    Anonymized · 20 voices
  • ElevenLabs TTS v4 Turbo$46.00/ 1M chars

    Generate fast text-to-speech audio using ElevenLabs Eleven-v4 Turbo. High-quality low-latency voices with audio tag support and automatic text normalization.

    Anonymized · 20 voices
  • ElevenLabs Turbo v2.5$62.50/ 1M chars

    ElevenLabs Turbo v2.5 is ElevenLabs’ low-latency multilingual speech model, balancing quality and speed for real-time use. It offers 21 voices and returns MP3 audio.

    Anonymized · 21 voices
  • Gemini 3.1 Flash TTS$188/ 1M chars

    Gemini 3.1 Flash TTS is Google’s Gemini-based speech model, which follows natural-language instructions for tone and pacing. It offers 30 voices and returns MP3, Opus or WAV audio.

    Anonymized · 30 voices
  • Gradium TTS$47.50/ 1M chars

    Gradium TTS is Gradium’s text-to-speech model for natural, low-latency voice generation. It offers 12 voices and returns WAV, PCM or Opus audio.

    Anonymized · 12 voices
  • Inworld TTS-1.5 Max$12.50/ 1M chars

    Inworld TTS-1.5 Max is the higher-quality tier of Inworld’s TTS-1.5 speech model, made for expressive delivery in games, companions and voice agents. It offers 14 voices and returns WAV audio.

    Anonymized · 14 voices
  • Kokoro Text to Speech$3.50/ 1M chars

    Kokoro is hexgrad’s open-weight 82M-parameter text-to-speech model. It speaks in 54 voices across several languages and returns MP3, Opus, AAC, FLAC, WAV or PCM audio.

    Private · 54 voices
  • MiniMax Speech-02 HD$125/ 1M chars

    Clone your voice from a short recording and generate natural speech in it across 30+ languages.

    Anonymized · 15 voices
  • Orpheus TTS$62.50/ 1M chars

    Orpheus TTS is Canopy Labs’ open-weight speech model, built on Llama 3B for natural, emotive delivery. It offers 8 voices and returns WAV audio.

    Private · 8 voices
  • Qwen 3 TTS 0.6B$87.50/ 1M chars

    Qwen 3 TTS 0.6B is the smaller of Alibaba’s two open-weight Qwen3-TTS models, built for fast, low-cost speech. It offers 9 voices and returns MP3 audio.

    Private · 9 voices
  • Qwen 3 TTS 1.7B$113/ 1M chars

    Qwen 3 TTS 1.7B is the larger of Alibaba’s two open-weight Qwen3-TTS models, trading some speed for higher-quality speech. It offers 9 voices and returns MP3 audio.

    Private · 9 voices
  • xAI TTS v1$18.75/ 1M chars

    xAI TTS v1 is xAI’s text-to-speech model, made for narration, assistants and voice apps. It offers 26 voices and returns MP3, WAV or PCM audio.

    Private · 26 voices

Catálogo de voces

Las voces son específicas de cada modelo. La voice que pases debe provenir del catálogo del model que hayas seleccionado. Elige un modelo abajo para explorar sus voces.

Chatterbox HD (Resemble AI) (tts-chatterbox-hd)

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

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

Gradium TTS (tts-gradium-v1)

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

Kokoro Text to Speech (tts-kokoro)

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

Orpheus TTS (tts-orpheus)

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

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

xAI TTS v1 (tts-xai-v1)

Los IDs de voz distinguen mayúsculas y minúsculas y solo son válidos para el model correspondiente. Pasa ambos campos juntos en la carga útil de tu solicitud. Consulta la API de voz para ejemplos.

Ejemplo de solicitud

Para cambiar de modelo, cambia tanto model como voice a un par del modelo seleccionado arriba.