Text to Speech AI Models
Convert text to natural speech with MiniMax Speech, ElevenLabs, Gemini TTS, Qwen TTS, Seed Speech, HeyGen and Grok TTS models.
All Text to Speech AI Models
Preview the output style, compare capabilities, then open any model for full specs, pricing, and a live Playground.
![Qwen 3 TTS - Text to Speech [0.6B] output preview](https://static.sandbase.ai/covers/alibaba/qwen-3-tts/0.6b/cover-flare-20261008043931.webp)
Qwen 3 TTS - Text to Speech [0.6B]
Qwen 3 Tts 0.6b is Alibaba's text-to-speech AI model. Generate human-like voiceovers with expressive intonation, multilingual support, and customizable voice characteristics.
MiniMax Voice Design
MiniMax Voice Design by MiniMax creates a new reusable voice from a text description of its timbre, age, and style, and returns a spoken preview.
MiniMax Speech 2.6 Turbo
MiniMax Speech 2.6 Turbo by MiniMax converts text into natural speech in 40+ languages with low latency, system or cloned voices, and emotion control.
MiniMax Speech 2.6 HD
MiniMax Speech 2.6 HD by MiniMax converts text into natural, high-fidelity speech in 40+ languages with system or cloned voices and emotion control.
Text To Dialogue
ElevenLabs Text to Dialogue uses Eleven v3 to turn a list of lines into a multi-speaker conversation, with a separate voice for each line and inline audio tags for delivery.
![Qwen 3 TTS - Text to Speech [1.7B] output preview](https://static.sandbase.ai/covers/alibaba/qwen-3-tts/1.7b/cover-flare-20261008045027.webp)
Qwen 3 TTS - Text to Speech [1.7B]
Qwen 3 Tts 1.7b is Alibaba's text-to-speech AI model. Generate human-like voiceovers with expressive intonation, multilingual support, and customizable voice characteristics.
MiniMax Speech 2.8 Turbo
MiniMax Speech 2.8 Turbo by MiniMax converts text into expressive speech in 40+ languages with low latency, system or cloned voices, and emotion control.
xAI Text to Speech
Grok Tts by xAI - convert text to natural-sounding speech with AI. Supports multiple voices, languages, emotions, and speaking styles for content creation and accessibility.
MiniMax Voice Clone
MiniMax Voice Clone by MiniMax creates a reusable custom voice from a reference recording of at least 10 seconds and returns a short preview spoken in that voice.
MiniMax Speech 2.8 HD
MiniMax Speech 2.8 HD by MiniMax converts text into expressive, high-fidelity speech in 40+ languages with system or cloned voices and emotion control.
Gemini 3.1 Flash Tts
Gemini 3.1 Flash Tts by Google - convert text to natural-sounding speech with AI. Supports multiple voices, languages, emotions, and speaking styles for content creation and accessibility.
Multilingual V2
Eleven Multilingual v2 is ElevenLabs' stable, lifelike text-to-speech model for 29 languages. Choose a voice, set stability and speaking speed, and turn written text into narration.
Turbo V2.5
Turbo V2.5 by ElevenLabs - convert text to natural-sounding speech with AI. Supports multiple voices, languages, emotions, and speaking styles for content creation and accessibility.
Bytedance Seed Speech Text to Speech
Seed Speech Tts 2.0 is Bytedance's text-to-speech AI model. Generate human-like voiceovers with expressive intonation, multilingual support, and customizable voice characteristics.
V3
Eleven v3 is ElevenLabs' expressive multilingual text-to-speech model. It follows inline audio tags such as [whispers] or [laughs] to direct delivery, emotion, and pacing.
ElevenLabs Eleven v4
Eleven v4 is ElevenLabs' most expressive text-to-speech model, with natural pacing, emotion and multilingual delivery.
ElevenLabs Eleven v4 Turbo
Eleven v4 Turbo is the low-latency tier of ElevenLabs' v4 text-to-speech generation, for real-time and high-volume narration.
Gemini 3.8 Flash Lite TTS
Gemini 3.8 Flash Lite TTS by Google turns text into expressive speech with 30 prebuilt voices and natural-language style direction.
Gemini 3.8 Flash TTS
Gemini 3.8 Flash TTS by Google turns text into expressive speech with 30 prebuilt voices and natural-language style direction.
HeyGen Voice
HeyGen Voice turns text into natural speech in 39 languages, with 24 public voices or a cloned voice from a reference recording.
HeyGen Voice Turbo
HeyGen Voice Turbo is the faster, lower-cost HeyGen text-to-speech model, with the same voices, languages and voice cloning.
Natural speech from text
Text-to-speech (TTS) models turn text into spoken audio in a chosen voice. Options range from fast, low-cost voices for agents and IVR to expressive HD voices for narration and video.
How to choose
- Quality or latency: MiniMax Speech offers HD and Turbo tiers; ElevenLabs has v3/v4 and Turbo models.
- Custom voices: MiniMax Voice Clone and Voice Design create a new voice from a sample or a description.
- Dialogue and dubbing: ElevenLabs Text to Dialogue and Dubbing handle multi-speaker scripts and translation.
Need music instead of speech? See text-to-music models. For talking-head video from audio, see lip-sync models.
Start using Text to Speech AI Models on SandBase
One API key and one request shape for every model on this page.
- 01
Create an API key
Sign in to the SandBase Console and create a key on the API Keys page. Keep it in an environment variable and never commit it to source control.
TERMINALexport SANDBASE_API_KEY="YOUR_SANDBASE_API_KEY" - 02
Submit a run
Send a request to the Unified Run API with model minimax/speech/2.8/hd. Only the model field changes between models on this page.
TERMINALcurl https://api.sandbase.ai/v1/run \ -H "Authorization: Bearer $SANDBASE_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model": "minimax/speech/2.8/hd", "text": "Hello, welcome to SandBase.", "voice_id": "Wise_Woman"}' - 03
Fetch the result
The response includes a run id. Poll it every few seconds until the status is completed, then download the output URL.
TERMINALcurl https://api.sandbase.ai/v1/run/$RUN_ID \ -H "Authorization: Bearer $SANDBASE_API_KEY"
Questions, answered
How do I pick a voice?
Most TTS models take a voice_id. The model page lists available voices and a default value you can start with.
Which languages are supported?
Coverage differs by model; check each model page for its language list.
Can I clone my own voice?
Yes, with voice-cloning endpoints such as MiniMax Voice Clone. Only clone voices you have the rights to use.
What audio format is returned?
An audio file URL, often with its duration. The model page lists the output fields.
Build with Text to Speech AI Models.
One key, consistent APIs, and usage-based pricing across every model on this page.