Model catalog
This text-to-speech leaderboard compares the available benchmark ranking, score status, per-character pricing and media capabilities without inventing scores for unranked models.
Data as of 2026-08-17
Browse the text-to-speech leaderboard ranking alongside the full catalog. Models without enough comparable benchmark evidence remain unscored.
Model | LLMBoard score | Input -> output | Native price | Provider | Context | Released |
|---|
| ModelSPSimba 3.2SpeechifyAI | LLMBoard score66.6 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelAL | LLMBoard score66.3 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelVLLuna TTSVUI Labs | LLMBoard score65.9 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelGO | LLMBoard score65.5 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelST | LLMBoard score65.2 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelCA | LLMBoard score64.8 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelIN | LLMBoard score64.4 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelSMLightning V3.1 Pro (Jul 2026)Smallest.ai | LLMBoard score64.1 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelIN | LLMBoard score63.7 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMI | LLMBoard score63.0 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMAFalcon 2Murf AI | LLMBoard score62.5 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelGRGradium TTS BetaGradium | LLMBoard score62.5 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMI | LLMBoard score61.7 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelASAsync Flash v1.5async | LLMBoard score61.7 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelST | LLMBoard score61.2 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelFAFish Audio S2.1 ProFish Audio | LLMBoard score60.8 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMI | LLMBoard score60.3 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelSMLightning V3.1 Pro TTS (Jun 2026)Smallest.ai | LLMBoard score60.3 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelIN | LLMBoard score59.8 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMI | LLMBoard score59.4 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelASAsync Pro v1.0async | LLMBoard score59.0 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMI | LLMBoard score58.7 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMI | LLMBoard score58.5 | Input -> outputtext -> audio | Native price$15 / 1M characters | ProviderMiniMax (minimax.io) | ContextN/A | ReleasedN/A |
| ModelFAFish Audio S2 ProFish Audio | LLMBoard score58.3 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelSPSimba 3.0SpeechifyAI | LLMBoard score57.9 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelXA | LLMBoard score57.4 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelST | LLMBoard score56.9 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelOP | LLMBoard score56.5 | Input -> outputtext -> audio | Native price$30 / 1M characters | ProviderOpenAI | ContextN/A | ReleasedN/A |
| ModelEL | LLMBoard score55.8 | Input -> outputtext -> audio | Native price$10 / 1M characters | ProviderElevenlabs | ContextN/A | ReleasedN/A |
| ModelEL | LLMBoard score55.7 | Input -> outputtext -> audio | Native price$30 / 1M characters | ProviderElevenlabs | ContextN/A | ReleasedN/A |
| ModelGRGradium TTSGradium | LLMBoard score55.4 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelRAChatterbox HDResemble AI | LLMBoard score55.0 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelOP | LLMBoard score54.7 | Input -> outputtext -> audio | Native price$15 / 1M characters | ProviderOpenAI | ContextN/A | ReleasedN/A |
| ModelGO | LLMBoard score54.3 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelGO | LLMBoard score53.1 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMA | LLMBoard score53.1 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelFAOpenAudio S1Fish Audio | LLMBoard score52.5 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelHISpeech 2.6Hithink | LLMBoard score52.2 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelEL | LLMBoard score52.0 | Input -> outputtext -> audio | Native price$15 / 1M characters | ProviderElevenlabs | ContextN/A | ReleasedN/A |
| ModelCA | LLMBoard score51.8 | Input -> outputtext -> audio | Native price$10 / 1M characters | ProviderCartesia | ContextN/A | ReleasedN/A |
| ModelOP | LLMBoard score51.5 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMRMaya 2 FlashMaya Research | LLMBoard score51.1 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelEL | LLMBoard score50.9 | Input -> outputtext -> audio | Native price$5 / 1M characters | ProviderElevenlabs | ContextN/A | ReleasedN/A |
| ModelGO | LLMBoard score50.7 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMI | LLMBoard score50.2 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelNV | LLMBoard score50.2 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelAM | LLMBoard score49.5 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelSPSIMBA 1.6SpeechifyAI | LLMBoard score49.5 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelXI | LLMBoard score48.9 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelKOKokoro 82M v1.0Kokoro | LLMBoard score48.5 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelGO | LLMBoard score48.0 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelHAOctave 2Hume AI | LLMBoard score48.0 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelGO | LLMBoard score47.5 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMI | LLMBoard score47.2 | Input -> outputtext -> audio | Native price$7.5 / 1M characters | ProviderMiniMax (minimax.io) | ContextN/A | ReleasedN/A |
| ModelRI | LLMBoard score47.1 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelASAsync Flash v1.0async | LLMBoard score46.8 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelFAOpenAudio S1 MiniFish Audio | LLMBoard score46.2 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMRMaya 2 GlobalMaya Research | LLMBoard score46.2 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMRMaya1Maya Research | LLMBoard score45.7 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelCA | LLMBoard score45.3 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelBAHiggs Audio V3 TTSBoson AI | LLMBoard score45.0 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelGO | LLMBoard score44.6 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelAM | LLMBoard score44.2 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelSPSIMBA 1.0SpeechifyAI | LLMBoard score43.9 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMI | LLMBoard score43.5 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMI | LLMBoard score43.0 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMI | LLMBoard score43.0 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelHAOctave TTSHume AI | LLMBoard score42.4 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelSMLightning v3.1Smallest.ai | LLMBoard score42.1 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelRAChatterboxResemble AI | LLMBoard score41.7 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelXI | LLMBoard score41.3 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelNV | LLMBoard score41.0 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelRI | LLMBoard score40.6 | Input -> outputtext -> audio | Native price$40 / 1M characters | ProviderRime | ContextN/A | ReleasedN/A |
| ModelZYZonos-v0.1Zyphra | LLMBoard score40.3 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMAMurf Speech Gen 2Murf AI | LLMBoard score39.9 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelLMLMNTLMNT | LLMBoard score39.5 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMI | LLMBoard score39.2 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMI | LLMBoard score38.8 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelOPOpenVoice v2OpenVoice | LLMBoard score38.5 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelNV | LLMBoard score38.1 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelAL | LLMBoard score37.7 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelNENeuphonic TTSNeuphonic | LLMBoard score37.4 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelAL | LLMBoard score37.0 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelCOXTTS v2Coqui | LLMBoard score36.6 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelGO | LLMBoard score36.3 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelRI | LLMBoard score35.9 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelSTStyleTTS 2StyleTTS | LLMBoard score35.6 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelGO | LLMBoard score35.2 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelAM | LLMBoard score34.8 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelGO | LLMBoard score34.5 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelNONoiz TTSNoiz | LLMBoard score34.1 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMEMetaVoice v1MetaVoice | LLMBoard score33.8 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelAM | LLMBoard score33.4 | Input -> outputtext -> audio | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelCA | LLMBoard scoreN/A | Input -> outputtext -> audio | Native price$10 / 1M characters | ProviderCartesia | ContextN/A | ReleasedN/A |
| ModelCA | LLMBoard scoreN/A | Input -> outputtext -> audio | Native price$15 / 1M characters | ProviderCartesia | ContextN/A | ReleasedN/A |
| ModelDE | LLMBoard scoreN/A | Input -> outputtext -> audio | Native price$15 / 1M characters | ProviderDeepgram | ContextN/A | ReleasedN/A |
| ModelDE | LLMBoard scoreN/A | Input -> outputtext -> audio | Native price$15 / 1M characters | ProviderDeepgram | ContextN/A | ReleasedN/A |
| ModelDE | LLMBoard scoreN/A | Input -> outputtext -> audio | Native price$15 / 1M characters | ProviderDeepgram | ContextN/A | ReleasedN/A |
| ModelEL | LLMBoard scoreN/A | Input -> outputtext -> audio | Native price$5 / 1M characters | ProviderElevenlabs | ContextN/A | ReleasedN/A |
| ModelIN | LLMBoard scoreN/A | Input -> outputtext -> audio | Native price$5 / 1M characters | ProviderInworld | ContextN/A | ReleasedN/A |
| ModelIN | LLMBoard scoreN/A | Input -> outputtext -> audio | Native price$10 / 1M characters | ProviderInworld | ContextN/A | ReleasedN/A |
| ModelMI | LLMBoard scoreN/A | Input -> outputtext -> audio | Native price$20 / 1M characters | ProviderMiniMax (minimax.io) | ContextN/A | ReleasedN/A |
| ModelMI | LLMBoard scoreN/A | Input -> outputtext -> audio | Native price$10 / 1M characters | ProviderMiniMax (minimax.io) | ContextN/A | ReleasedN/A |
| ModelPL | LLMBoard scoreN/A | Input -> outputtext -> audio | Native price$50 / 1M characters | ProviderGroq | ContextN/A | ReleasedN/A |
This leaderboard uses evaluation and benchmark evidence only for scores. Price, context and model specifications remain separate from the ranking.
Use price as context for the leaderboard, not as part of its benchmark ranking. Each listing keeps its original unit.
Compare input and output support alongside the leaderboard; modality support does not change the benchmark ranking.
93 models currently have a domain-specific LLMBoard score. The leaderboard ranking uses matched benchmark evidence, while coverage and provisional status identify incomplete evidence.
Prices retain the unit returned by the catalog, such as per image, per second, per minute or per million characters. They are never shown as token prices.
Some models do not have a current price listing in their native billing unit.