What is Spark-TTS?
Spark-TTS is listed under AI Voice & Speech, in the Content & Media Generation category on Flocci AI Tools. LLM-based TTS with BiCodec single-stream tokens. It is free, with no paid plan attached, and it lives at github.com.
What Spark-TTS does
- LLM-based TTS with BiCodec single-stream tokens
- Zero-shot cloning and controllable pitch/speed/gender for Chinese and English
- Apache-2.0 weights
Spark-TTS — straight answers
Is Spark-TTS free?
Spark-TTS is listed as fully free — there is no paid tier attached to it in the catalog. That makes it one of the 399 entries on Flocci AI Tools with no upgrade path built in.
What can Spark-TTS do?
Spark-TTS does 3 things the catalog singles out: Llm-based tts with bicodec single-stream tokens; zero-shot cloning and controllable pitch/speed/gender for chinese and english; apache-2.0 weights.
What is the best free alternative to Spark-TTS?
Chatterbox (Resemble AI) is the closest free alternative: it sits in the same AI Voice & Speech sub-category and is free. Copilot Audio Expressions, CosyVoice and F5-TTS also start free. The full list is on the alternatives page.
See the full list →Spark-TTS alternatives
Compare all alternatives →ElevenLabs
AI Voice & Speech
- Most natural text-to-speech and voice cloning
- Dubbing into 30+ languages
- Voice design and a huge voice library
- Free monthly characters
- Realistic, low-latency text-to-speech
- Voice cloning and voice agents
- 800+ voices, many languages
- Free trial words
- Studio-quality voiceovers for videos
- Sync voice with slides and media
- Voice changer and cloning
- Free trial minutes
Cartesia
AI Voice & Speech
- Ultra-low-latency real-time voice (Sonic)
- Ideal for voice agents and calls
- Instant voice cloning
- Free tier for developers
Hume AI
AI Voice & Speech
- Emotionally expressive voice interface (EVI)
- Detects and responds to tone
- Customizable empathic voices
- Free developer credits
Fish Audio
AI Voice & Speech
- 15-second voice cloning claimed near-perfect fidelity
- S2.1 Pro real-time emotionally-controllable voice model, free to start for devs
- Bundles TTS, voice cloning, STT and a full voice-agent stack in one platform