{"data":[{"id":"assemblyai/assemblyai-tts-1","canonical_slug":"assemblyai/assemblyai-tts-1-20261028","hugging_face_id":null,"name":"AssemblyAI: TTS 1","created":1793217672,"description":"AssemblyAI TTS 1 is a text-to-speech model from AssemblyAI. It is suited for voice agents, narration, and multilingual applications, and draws on a public library of several thousand voices across...","context_length":0,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000015","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":["aai-antonioluis","aai-audrey","aai-carrie","aai-constanza","aai-donatien","aai-ernest","aai-ewald","aai-gunther","aai-hailey","aai-jorg","aai-kyla","aai-magdalena","aai-malvina","aai-nancy","aai-oriol","aai-peter","aai-sara","aai-steven","aai-titus","aai-troy"],"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/assemblyai/assemblyai-tts-1-20261028/endpoints"},"endpoints":["/api/v1/audio/speech"]},{"id":"heygen/heygen-voice-1-turbo","canonical_slug":"heygen/heygen-voice-1-turbo-20261009","hugging_face_id":null,"name":"HeyGen: HeyGen Voice Turbo","created":1793030422,"description":"HeyGen Voice Turbo is a lower-latency version of HeyGen Voice, HeyGen's text-to-speech model. It has the same 10 default voices, or bring your own HeyGen key to use voice clones...","context_length":0,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000004","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":["nadine","tabitha","bram","gareth","noelle","meredith","sabrina","lucian","weston","vincent"],"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/heygen/heygen-voice-1-turbo-20261009/endpoints"},"endpoints":["/api/v1/audio/speech"]},{"id":"heygen/heygen-voice-1-turbo:free","canonical_slug":"heygen/heygen-voice-1-turbo-20261009","hugging_face_id":null,"name":"HeyGen: HeyGen Voice Turbo (free)","created":1793030422,"description":"HeyGen Voice Turbo is a lower-latency version of HeyGen Voice, HeyGen's text-to-speech model. It has the same 10 default voices, or bring your own HeyGen key to use voice clones...","context_length":0,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":["nadine","tabitha","bram","gareth","noelle","meredith","sabrina","lucian","weston","vincent"],"knowledge_cutoff":null,"expiration_date":"2026-11-30","links":{"details":"/api/v1/models/heygen/heygen-voice-1-turbo-20261009/endpoints"},"endpoints":["/api/v1/audio/speech"]},{"id":"mistralai/voxtral-mini-tts-3-0","canonical_slug":"mistralai/voxtral-mini-tts-3-0-20261020","hugging_face_id":null,"name":"Mistral: Voxtral TTS 3","created":1792512813,"description":"Voxtral TTS 3 is Mistral's text-to-speech model. It converts text into natural-sounding speech, offers a library of preset voices, supports zero-shot voice cloning, and accepts emotion and pace tags in...","context_length":4096,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.000013","completion":"0"},"top_provider":{"context_length":4096,"max_completion_tokens":3276,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":["voice_3150","voice_478","voice_447","voice_485","en_paul_sad","en_paul_neutral","en_paul_happy","en_paul_frustrated","en_paul_excited","en_paul_confident","en_paul_cheerful","en_paul_angry","voice_3149","voice_3147","voice_591","voice_590","voice_1788","voice_1787","voice_1786","gb_oliver_neutral","gb_jane_sarcasm","gb_jane_confused","gb_oliver_sad","gb_oliver_excited","gb_oliver_curious","gb_oliver_confident","gb_oliver_cheerful","gb_oliver_angry","gb_jane_shameful","gb_jane_sad","gb_jane_neutral","gb_jane_jealousy","gb_jane_frustrated","gb_jane_curious","gb_jane_confident","voice_479","voice_3143","voice_481","voice_483","voice_592","voice_3137","voice_589","voice_3141","fr_marie_sad","fr_marie_neutral","fr_marie_happy","fr_marie_excited","fr_marie_curious","fr_marie_angry","voice_3153","voice_3139","voice_3146","voice_482","voice_3133","voice_3136","voice_3135","voice_3145","voice_3134","voice_3154","voice_480","voice_3155","voice_3132","voice_3138","voice_3140","voice_3144","voice_3142"],"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/mistralai/voxtral-mini-tts-3-0-20261020/endpoints"},"endpoints":["/api/v1/audio/speech"]},{"id":"heygen/heygen-voice-1","canonical_slug":"heygen/heygen-voice-1-20261009","hugging_face_id":null,"name":"HeyGen: HeyGen Voice","created":1791929559,"description":"HeyGen Voice is a text-to-speech model from HeyGen. It comes with 10 default voices, or bring your own HeyGen key to use voice clones from your own account. It streams...","context_length":0,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000015","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":["nadine","tabitha","bram","gareth","noelle","meredith","sabrina","lucian","weston","vincent"],"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/heygen/heygen-voice-1-20261009/endpoints"},"endpoints":["/api/v1/audio/speech"]},{"id":"fish-audio/drama-3","canonical_slug":"fish-audio/drama-3-20261013","hugging_face_id":null,"name":"Fish Audio: Drama 3","created":1791910176,"description":"Drama 3 is a text-to-speech model from Fish Audio built for directed voice performances. You write the direction in plain language in square brackets before a line, such as `[nervous,...","context_length":0,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000002","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/fish-audio/drama-3-20261013/endpoints"},"endpoints":["/api/v1/audio/speech"],"benchmarks":{"design_arena":[{"arena":"models","category":"audiorealism","elo":958,"win_rate":34.2,"rank":4}]}},{"id":"elevenlabs/eleven-v4","canonical_slug":"elevenlabs/eleven-v4-20260930","hugging_face_id":null,"name":"ElevenLabs: Eleven v4","created":1791386285,"description":"Eleven v4 is a text-to-speech model from ElevenLabs. It is ElevenLabs' most expressive model, with inline audio tags for emotional and delivery control, support for 90+ languages, and a 10,000-character...","context_length":0,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00008","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":["george","sarah","adam","alice","bella","bill","brian","callum","charlie","chris","daniel","eric","harry","jessica","laura","liam","lily","matilda","river","roger","will"],"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/elevenlabs/eleven-v4-20260930/endpoints"},"endpoints":["/api/v1/audio/speech"]},{"id":"elevenlabs/eleven-v4-turbo","canonical_slug":"elevenlabs/eleven-v4-turbo-20260930","hugging_face_id":null,"name":"ElevenLabs: Eleven v4 Turbo","created":1791386280,"description":"Eleven v4 Turbo is a low-latency text-to-speech model from ElevenLabs. It keeps Eleven v4's expressive delivery and audio tags while being tuned for faster generation, with support for 90+ languages...","context_length":0,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00004","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":["george","sarah","adam","alice","bella","bill","brian","callum","charlie","chris","daniel","eric","harry","jessica","laura","liam","lily","matilda","river","roger","will"],"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/elevenlabs/eleven-v4-turbo-20260930/endpoints"},"endpoints":["/api/v1/audio/speech"]},{"id":"elevenlabs/eleven-v3","canonical_slug":"elevenlabs/eleven-v3-20260930","hugging_face_id":null,"name":"ElevenLabs: Eleven v3","created":1791386272,"description":"Eleven v3 is a text-to-speech model from ElevenLabs. It produces emotionally rich, highly expressive speech with inline audio tags, supports 70+ languages, and has a 5,000-character request limit.","context_length":0,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00008","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":["george","sarah","adam","alice","bella","bill","brian","callum","charlie","chris","daniel","eric","harry","jessica","laura","liam","lily","matilda","river","roger","will"],"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/elevenlabs/eleven-v3-20260930/endpoints"},"endpoints":["/api/v1/audio/speech"]},{"id":"elevenlabs/eleven-v3-conversational","canonical_slug":"elevenlabs/eleven-v3-conversational-20260930","hugging_face_id":null,"name":"ElevenLabs: Eleven v3 Conversational","created":1791386266,"description":"Eleven v3 Conversational is a text-to-speech model from ElevenLabs, a variant of Eleven v3 optimized for natural dialogue in conversational agents. It supports 70+ languages and has a 5,000-character request...","context_length":0,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00004","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":["george","sarah","adam","alice","bella","bill","brian","callum","charlie","chris","daniel","eric","harry","jessica","laura","liam","lily","matilda","river","roger","will"],"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/elevenlabs/eleven-v3-conversational-20260930/endpoints"},"endpoints":["/api/v1/audio/speech"]},{"id":"elevenlabs/eleven-flash-v2.5","canonical_slug":"elevenlabs/eleven-flash-v2.5-20260930","hugging_face_id":null,"name":"ElevenLabs: Eleven Flash v2.5","created":1791386250,"description":"Eleven Flash v2.5 is an ultra-low-latency text-to-speech model from ElevenLabs. It is suited for conversational and real-time use cases, supports 32 languages, and has a 40,000-character request limit.","context_length":0,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00004","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":["george","sarah","adam","alice","bella","bill","brian","callum","charlie","chris","daniel","eric","harry","jessica","laura","liam","lily","matilda","river","roger","will"],"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/elevenlabs/eleven-flash-v2.5-20260930/endpoints"},"endpoints":["/api/v1/audio/speech"]},{"id":"elevenlabs/eleven-turbo-v2","canonical_slug":"elevenlabs/eleven-turbo-v2-20260930","hugging_face_id":null,"name":"ElevenLabs: Eleven Turbo v2","created":1791386238,"description":"Eleven Turbo v2 is an English-only, low-latency text-to-speech model from ElevenLabs. It is suited for developer use cases where speed matters and only English is needed, and has a 30,000-character...","context_length":0,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00004","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":["george","sarah","adam","alice","bella","bill","brian","callum","charlie","chris","daniel","eric","harry","jessica","laura","liam","lily","matilda","river","roger","will"],"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/elevenlabs/eleven-turbo-v2-20260930/endpoints"},"endpoints":["/api/v1/audio/speech"]},{"id":"elevenlabs/eleven-multilingual-v2","canonical_slug":"elevenlabs/eleven-multilingual-v2-20260930","hugging_face_id":null,"name":"ElevenLabs: Eleven Multilingual v2","created":1791386232,"description":"Eleven Multilingual v2 is a text-to-speech model from ElevenLabs. It is suited for lifelike, consistent long-form narration such as voice-overs and audiobooks, supports 29 languages, and has a 10,000-character request...","context_length":0,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00008","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":["george","sarah","adam","alice","bella","bill","brian","callum","charlie","chris","daniel","eric","harry","jessica","laura","liam","lily","matilda","river","roger","will"],"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/elevenlabs/eleven-multilingual-v2-20260930/endpoints"},"endpoints":["/api/v1/audio/speech"]},{"id":"elevenlabs/eleven-turbo-v2.5","canonical_slug":"elevenlabs/eleven-turbo-v2.5-20260930","hugging_face_id":null,"name":"ElevenLabs: Eleven Turbo v2.5","created":1791386218,"description":"Eleven Turbo v2.5 is a low-latency text-to-speech model from ElevenLabs. It balances quality and speed for developer use cases that need non-English languages, supports 32 languages, and has a 40,000-character...","context_length":0,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00004","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":["george","sarah","adam","alice","bella","bill","brian","callum","charlie","chris","daniel","eric","harry","jessica","laura","liam","lily","matilda","river","roger","will"],"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/elevenlabs/eleven-turbo-v2.5-20260930/endpoints"},"endpoints":["/api/v1/audio/speech"]},{"id":"elevenlabs/eleven-flash-v2","canonical_slug":"elevenlabs/eleven-flash-v2-20260930","hugging_face_id":null,"name":"ElevenLabs: Eleven Flash v2","created":1791386207,"description":"Eleven Flash v2 is an English-only, ultra-low-latency text-to-speech model from ElevenLabs. It is suited for conversational and real-time English use cases, and has a 30,000-character request limit.","context_length":0,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00004","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":["george","sarah","adam","alice","bella","bill","brian","callum","charlie","chris","daniel","eric","harry","jessica","laura","liam","lily","matilda","river","roger","will"],"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/elevenlabs/eleven-flash-v2-20260930/endpoints"},"endpoints":["/api/v1/audio/speech"]},{"id":"microsoft/mai-voice-2.1-flash","canonical_slug":"microsoft/mai-voice-2.1-flash-20261001","hugging_face_id":null,"name":"Microsoft AI: MAI-Voice-2.1-Flash","created":1790870485,"description":"MAI-Voice-2.1-Flash is a low-latency text-to-speech model from Microsoft AI, optimized for real-time responsiveness. It produces natural, expressive speech across 23 languages, with human-like intonation, rhythm, and emotional nuance. It is...","context_length":0,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000015","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":["cs-CZ-Grant:MAI-Voice-2.1-Flash","cs-CZ-Harper:MAI-Voice-2.1-Flash","da-DK-Grant:MAI-Voice-2.1-Flash","da-DK-Harper:MAI-Voice-2.1-Flash","de-DE-Grant:MAI-Voice-2.1-Flash","de-DE-Harper:MAI-Voice-2.1-Flash","de-DE-Klaus:MAI-Voice-2.1-Flash","de-DE-Mia:MAI-Voice-2.1-Flash","en-AU-Isla:MAI-Voice-2.1-Flash","en-GB-Emily:MAI-Voice-2.1-Flash","en-GB-Harry:MAI-Voice-2.1-Flash","en-IN-Dhruv:MAI-Voice-2.1-Flash","en-IN-Priya:MAI-Voice-2.1-Flash","en-US-Ethan:MAI-Voice-2.1-Flash","en-US-Grant:MAI-Voice-2.1-Flash","en-US-Harper:MAI-Voice-2.1-Flash","en-US-Iris:MAI-Voice-2.1-Flash","en-US-Jasper:MAI-Voice-2.1-Flash","en-US-Olivia:MAI-Voice-2.1-Flash","en-US-Sage:MAI-Voice-2.1-Flash","es-ES-Marta:MAI-Voice-2.1-Flash","es-MX-Alejo:MAI-Voice-2.1-Flash","es-MX-Grant:MAI-Voice-2.1-Flash","es-MX-Harper:MAI-Voice-2.1-Flash","es-MX-Valeria:MAI-Voice-2.1-Flash","fi-FI-Grant:MAI-Voice-2.1-Flash","fi-FI-Harper:MAI-Voice-2.1-Flash","fr-FR-Grant:MAI-Voice-2.1-Flash","fr-FR-Harper:MAI-Voice-2.1-Flash","fr-FR-Marc:MAI-Voice-2.1-Flash","fr-FR-Soleil:MAI-Voice-2.1-Flash","hi-IN-Arjun:MAI-Voice-2.1-Flash","hi-IN-Dhruv:MAI-Voice-2.1-Flash","hi-IN-Grant:MAI-Voice-2.1-Flash","hi-IN-Harper:MAI-Voice-2.1-Flash","hi-IN-Kavya:MAI-Voice-2.1-Flash","hi-IN-Priya:MAI-Voice-2.1-Flash","hu-HU-Bence:MAI-Voice-2.1-Flash","hu-HU-Grant:MAI-Voice-2.1-Flash","hu-HU-Harper:MAI-Voice-2.1-Flash","hu-HU-Levente:MAI-Voice-2.1-Flash","hu-HU-Lilla:MAI-Voice-2.1-Flash","hu-HU-Reka:MAI-Voice-2.1-Flash","id-ID-Grant:MAI-Voice-2.1-Flash","id-ID-Harper:MAI-Voice-2.1-Flash","it-IT-Grant:MAI-Voice-2.1-Flash","it-IT-Harper:MAI-Voice-2.1-Flash","it-IT-Luca:MAI-Voice-2.1-Flash","it-IT-Rosa:MAI-Voice-2.1-Flash","ko-KR-Grant:MAI-Voice-2.1-Flash","ko-KR-Haena:MAI-Voice-2.1-Flash","ko-KR-Harper:MAI-Voice-2.1-Flash","ko-KR-Junho:MAI-Voice-2.1-Flash","nb-NO-Grant:MAI-Voice-2.1-Flash","nb-NO-Harper:MAI-Voice-2.1-Flash","nl-NL-Grant:MAI-Voice-2.1-Flash","nl-NL-Harper:MAI-Voice-2.1-Flash","nl-NL-Sander:MAI-Voice-2.1-Flash","pl-PL-Grant:MAI-Voice-2.1-Flash","pl-PL-Harper:MAI-Voice-2.1-Flash","pt-BR-Caio:MAI-Voice-2.1-Flash","pt-BR-Grant:MAI-Voice-2.1-Flash","pt-BR-Harper:MAI-Voice-2.1-Flash","pt-BR-Luana:MAI-Voice-2.1-Flash","pt-BR-Pedro:MAI-Voice-2.1-Flash","pt-BR-Rafael:MAI-Voice-2.1-Flash","pt-PT-Grant:MAI-Voice-2.1-Flash","pt-PT-Harper:MAI-Voice-2.1-Flash","pt-PT-Rui:MAI-Voice-2.1-Flash","ro-RO-Andrei:MAI-Voice-2.1-Flash","ro-RO-Elena:MAI-Voice-2.1-Flash","ro-RO-Grant:MAI-Voice-2.1-Flash","ro-RO-Harper:MAI-Voice-2.1-Flash","ro-RO-Ioana:MAI-Voice-2.1-Flash","ro-RO-Radu:MAI-Voice-2.1-Flash","ru-RU-Grant:MAI-Voice-2.1-Flash","ru-RU-Harper:MAI-Voice-2.1-Flash","ru-RU-Lev:MAI-Voice-2.1-Flash","ru-RU-Masha:MAI-Voice-2.1-Flash","sv-SE-Grant:MAI-Voice-2.1-Flash","sv-SE-Harper:MAI-Voice-2.1-Flash","th-TH-Grant:MAI-Voice-2.1-Flash","th-TH-Harper:MAI-Voice-2.1-Flash","th-TH-Krit:MAI-Voice-2.1-Flash","th-TH-Nattapong:MAI-Voice-2.1-Flash","tr-TR-Aydin:MAI-Voice-2.1-Flash","tr-TR-Elif:MAI-Voice-2.1-Flash","tr-TR-Grant:MAI-Voice-2.1-Flash","tr-TR-Harper:MAI-Voice-2.1-Flash","vi-VN-Grant:MAI-Voice-2.1-Flash","vi-VN-Harper:MAI-Voice-2.1-Flash","zh-CN-Bo:MAI-Voice-2.1-Flash","zh-CN-Grant:MAI-Voice-2.1-Flash","zh-CN-Harper:MAI-Voice-2.1-Flash","zh-CN-Lan:MAI-Voice-2.1-Flash","zh-CN-Mei:MAI-Voice-2.1-Flash","zh-CN-Wei:MAI-Voice-2.1-Flash"],"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/microsoft/mai-voice-2.1-flash-20261001/endpoints"},"endpoints":["/api/v1/audio/speech"]},{"id":"microsoft/mai-voice-2.1","canonical_slug":"microsoft/mai-voice-2.1-20261001","hugging_face_id":null,"name":"Microsoft AI: MAI-Voice-2.1","created":1790870467,"description":"MAI-Voice-2.1 is Microsoft AI's highest-fidelity, most expressive text-to-speech model. It produces natural, studio-grade speech across 23 languages, with detailed prosody, nuanced expressiveness, and speaker consistency over long-form content. It is...","context_length":0,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000022","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":["cs-CZ-Grant:MAI-Voice-2.1","cs-CZ-Harper:MAI-Voice-2.1","da-DK-Grant:MAI-Voice-2.1","da-DK-Harper:MAI-Voice-2.1","de-DE-Grant:MAI-Voice-2.1","de-DE-Harper:MAI-Voice-2.1","de-DE-Klaus:MAI-Voice-2.1","de-DE-Mia:MAI-Voice-2.1","en-AU-Isla:MAI-Voice-2.1","en-GB-Emily:MAI-Voice-2.1","en-GB-Harry:MAI-Voice-2.1","en-IN-Dhruv:MAI-Voice-2.1","en-IN-Priya:MAI-Voice-2.1","en-US-Ethan:MAI-Voice-2.1","en-US-Grant:MAI-Voice-2.1","en-US-Harper:MAI-Voice-2.1","en-US-Iris:MAI-Voice-2.1","en-US-Jasper:MAI-Voice-2.1","en-US-Olivia:MAI-Voice-2.1","en-US-Sage:MAI-Voice-2.1","es-ES-Marta:MAI-Voice-2.1","es-MX-Alejo:MAI-Voice-2.1","es-MX-Grant:MAI-Voice-2.1","es-MX-Harper:MAI-Voice-2.1","es-MX-Valeria:MAI-Voice-2.1","fi-FI-Grant:MAI-Voice-2.1","fi-FI-Harper:MAI-Voice-2.1","fr-FR-Grant:MAI-Voice-2.1","fr-FR-Harper:MAI-Voice-2.1","fr-FR-Marc:MAI-Voice-2.1","fr-FR-Soleil:MAI-Voice-2.1","hi-IN-Arjun:MAI-Voice-2.1","hi-IN-Dhruv:MAI-Voice-2.1","hi-IN-Grant:MAI-Voice-2.1","hi-IN-Harper:MAI-Voice-2.1","hi-IN-Kavya:MAI-Voice-2.1","hi-IN-Priya:MAI-Voice-2.1","hu-HU-Bence:MAI-Voice-2.1","hu-HU-Grant:MAI-Voice-2.1","hu-HU-Harper:MAI-Voice-2.1","hu-HU-Levente:MAI-Voice-2.1","hu-HU-Lilla:MAI-Voice-2.1","hu-HU-Reka:MAI-Voice-2.1","id-ID-Grant:MAI-Voice-2.1","id-ID-Harper:MAI-Voice-2.1","it-IT-Grant:MAI-Voice-2.1","it-IT-Harper:MAI-Voice-2.1","it-IT-Luca:MAI-Voice-2.1","it-IT-Rosa:MAI-Voice-2.1","ko-KR-Grant:MAI-Voice-2.1","ko-KR-Haena:MAI-Voice-2.1","ko-KR-Harper:MAI-Voice-2.1","ko-KR-Junho:MAI-Voice-2.1","nb-NO-Grant:MAI-Voice-2.1","nb-NO-Harper:MAI-Voice-2.1","nl-NL-Grant:MAI-Voice-2.1","nl-NL-Harper:MAI-Voice-2.1","nl-NL-Sander:MAI-Voice-2.1","pl-PL-Grant:MAI-Voice-2.1","pl-PL-Harper:MAI-Voice-2.1","pt-BR-Caio:MAI-Voice-2.1","pt-BR-Grant:MAI-Voice-2.1","pt-BR-Harper:MAI-Voice-2.1","pt-BR-Luana:MAI-Voice-2.1","pt-BR-Pedro:MAI-Voice-2.1","pt-BR-Rafael:MAI-Voice-2.1","pt-PT-Grant:MAI-Voice-2.1","pt-PT-Harper:MAI-Voice-2.1","pt-PT-Rui:MAI-Voice-2.1","ro-RO-Andrei:MAI-Voice-2.1","ro-RO-Elena:MAI-Voice-2.1","ro-RO-Grant:MAI-Voice-2.1","ro-RO-Harper:MAI-Voice-2.1","ro-RO-Ioana:MAI-Voice-2.1","ro-RO-Radu:MAI-Voice-2.1","ru-RU-Grant:MAI-Voice-2.1","ru-RU-Harper:MAI-Voice-2.1","ru-RU-Lev:MAI-Voice-2.1","ru-RU-Masha:MAI-Voice-2.1","sv-SE-Grant:MAI-Voice-2.1","sv-SE-Harper:MAI-Voice-2.1","th-TH-Grant:MAI-Voice-2.1","th-TH-Harper:MAI-Voice-2.1","th-TH-Krit:MAI-Voice-2.1","th-TH-Nattapong:MAI-Voice-2.1","tr-TR-Aydin:MAI-Voice-2.1","tr-TR-Elif:MAI-Voice-2.1","tr-TR-Grant:MAI-Voice-2.1","tr-TR-Harper:MAI-Voice-2.1","vi-VN-Grant:MAI-Voice-2.1","vi-VN-Harper:MAI-Voice-2.1","zh-CN-Bo:MAI-Voice-2.1","zh-CN-Grant:MAI-Voice-2.1","zh-CN-Harper:MAI-Voice-2.1","zh-CN-Lan:MAI-Voice-2.1","zh-CN-Mei:MAI-Voice-2.1","zh-CN-Wei:MAI-Voice-2.1"],"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/microsoft/mai-voice-2.1-20261001/endpoints"},"endpoints":["/api/v1/audio/speech"]},{"id":"bytedance-seed/seed-audio-1-0","canonical_slug":"bytedance-seed/seed-audio-1-0-20260630","hugging_face_id":null,"name":"ByteDance Seed: Seed Audio 1.0","created":1790372476,"description":"Seed Audio 1.0 is ByteDance Seed's non-streaming audio generation model. It produces speech and other audio from a natural-language text prompt that can describe the desired voice, tone, and sound...","context_length":0,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0.0025"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/bytedance-seed/seed-audio-1-0-20260630/endpoints"},"endpoints":["/api/v1/audio/speech"]},{"id":"google/gemini-3.8-flash-lite-tts","canonical_slug":"google/gemini-3.8-flash-lite-tts-20260922","hugging_face_id":null,"name":"Google: Gemini 3.8 Flash Lite TTS","created":1790200276,"description":"Gemini 3.8 Flash Lite TTS is a text-to-speech model from Google and the fast, high-throughput member of the 3.8 TTS family alongside [Gemini 3.8 Flash TTS](https://openrouter.ai/google/gemini-3.8-flash-tts). It is suited for...","context_length":32768,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.0000005","completion":"0.000006"},"top_provider":{"context_length":32768,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":["Zephyr","Puck","Charon","Kore","Fenrir","Leda","Orus","Aoede","Callirrhoe","Autonoe","Enceladus","Iapetus","Umbriel","Algieba","Despina","Erinome","Algenib","Rasalgethi","Laomedeia","Achernar","Alnilam","Schedar","Gacrux","Pulcherrima","Achird","Zubenelgenubi","Vindemiatrix","Sadachbia","Sadaltager","Sulafat"],"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-3.8-flash-lite-tts-20260922/endpoints"},"endpoints":["/api/v1/audio/speech"]},{"id":"google/gemini-3.8-flash-tts","canonical_slug":"google/gemini-3.8-flash-tts-20260922","hugging_face_id":null,"name":"Google: Gemini 3.8 Flash TTS","created":1790200266,"description":"Gemini 3.8 Flash TTS is a text-to-speech model from Google and the successor to [Gemini 3.1 Flash TTS Preview](https://openrouter.ai/google/gemini-3.1-flash-tts-preview). It is the creative tier of the 3.8 TTS family, suited...","context_length":32768,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.0000005","completion":"0.000009"},"top_provider":{"context_length":32768,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":["Zephyr","Puck","Charon","Kore","Fenrir","Leda","Orus","Aoede","Callirrhoe","Autonoe","Enceladus","Iapetus","Umbriel","Algieba","Despina","Erinome","Algenib","Rasalgethi","Laomedeia","Achernar","Alnilam","Schedar","Gacrux","Pulcherrima","Achird","Zubenelgenubi","Vindemiatrix","Sadachbia","Sadaltager","Sulafat"],"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-3.8-flash-tts-20260922/endpoints"},"endpoints":["/api/v1/audio/speech"],"benchmarks":{"design_arena":[{"arena":"models","category":"audiorealism","elo":1080,"win_rate":48.2,"rank":3},{"arena":"models","category":"text-to-speech","elo":1456,"win_rate":77.9,"rank":1}]}},{"id":"deepgram/flux-tts","canonical_slug":"deepgram/flux-tts-20260812","hugging_face_id":null,"name":"Deepgram: Flux TTS","created":1786574888,"description":"Flux TTS is a text-to-speech model from Deepgram. It is suited for natural, expressive English speech synthesis across Deepgram's Flux voice catalog.","context_length":0,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000045","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":["flux-alexis-en","flux-bree-en","flux-brittany-en","flux-brooke-en","flux-bruce-en","flux-cliff-en","flux-cole-en","flux-colin-en","flux-conor-en","flux-donovan-en","flux-drew-en","flux-elise-en","flux-gemma-en","flux-haley-en","flux-hannah-en","flux-heather-en","flux-jack-en","flux-kai-en","flux-kelsey-en","flux-kit-en","flux-maeve-en","flux-marcelo-en","flux-marcus-en","flux-meena-en","flux-meghan-en","flux-miles-en","flux-naveen-en","flux-paige-en","flux-priya-en","flux-rufus-en","flux-sean-en","flux-sharon-en","flux-sienna-en","flux-tanner-en","flux-wade-en","flux-wes-en"],"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepgram/flux-tts-20260812/endpoints"},"endpoints":["/api/v1/audio/speech"]},{"id":"fish-audio/s1","canonical_slug":"fish-audio/s1-20260729","hugging_face_id":null,"name":"Fish Audio: S1","created":1785353734,"description":"S1 is a multilingual text-to-speech model from Fish Audio. It is suited for voice applications that need broad emotional expression, using parenthetical controls to guide speaking style across its supported...","context_length":0,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000015","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/fish-audio/s1-20260729/endpoints"},"endpoints":["/api/v1/audio/speech"]},{"id":"fish-audio/s2-pro","canonical_slug":"fish-audio/s2-pro-20260729","hugging_face_id":null,"name":"Fish Audio: S2 Pro","created":1785353734,"description":"S2 Pro is a multilingual text-to-speech model from Fish Audio. It is suited for expressive narration and multi-speaker dialogue, with natural-language controls for speaking style and emotion.","context_length":0,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000015","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/fish-audio/s2-pro-20260729/endpoints"},"endpoints":["/api/v1/audio/speech"]},{"id":"fish-audio/s2.1-pro-free:free","canonical_slug":"fish-audio/s2.1-pro-free-20260729","hugging_face_id":null,"name":"Fish Audio: S2.1 Pro Free (free)","created":1785353733,"description":"S2.1 Pro Free is the no-cost variant of Fish Audio S2.1 Pro, intended for testing, prototyping, and low-volume applications. It provides the same synthesis capabilities without production latency or availability...","context_length":0,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/fish-audio/s2.1-pro-free-20260729/endpoints"},"endpoints":["/api/v1/audio/speech"]},{"id":"fish-audio/s2.1-pro","canonical_slug":"fish-audio/s2.1-pro-20260729","hugging_face_id":null,"name":"Fish Audio: S2.1 Pro","created":1785353732,"description":"S2.1 Pro is a production-oriented text-to-speech model from Fish Audio. It is suited for multilingual voice applications, expressive narration, and dialogue synthesis, with open-ended natural-language controls for speaking style and...","context_length":0,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000015","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/fish-audio/s2.1-pro-20260729/endpoints"},"endpoints":["/api/v1/audio/speech"],"benchmarks":{"design_arena":[{"arena":"models","category":"audiorealism","elo":953,"win_rate":33.2,"rank":5}]}},{"id":"microsoft/mai-voice-2-flash","canonical_slug":"microsoft/mai-voice-2-flash-20260723","hugging_face_id":null,"name":"Microsoft AI: MAI-Voice-2-Flash","created":1784822080,"description":"MAI-Voice-2-Flash is a low-latency text-to-speech model from Microsoft AI for voice agents, assistants, call centers, accessibility, narration, and other interactive applications. It generates expressive 24 kHz mono speech across 15...","context_length":0,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000015","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":["en-US-Harper:MAI-Voice-2","es-MX-Valeria:MAI-Voice-2","fr-FR-Soleil:MAI-Voice-2","de-DE-Klaus:MAI-Voice-2"],"knowledge_cutoff":null,"expiration_date":"2026-12-31","links":{"details":"/api/v1/models/microsoft/mai-voice-2-flash-20260723/endpoints"},"endpoints":["/api/v1/audio/speech"],"benchmarks":{"design_arena":[{"arena":"models","category":"audiorealism","elo":1137,"win_rate":51.2,"rank":2},{"arena":"models","category":"text-to-speech","elo":1122,"win_rate":43.7,"rank":3}]}},{"id":"qwen/qwen-audio-3.0-tts-flash","canonical_slug":"qwen/qwen-audio-3.0-tts-flash-20260723","hugging_face_id":null,"name":"Qwen: Qwen-Audio-3.0-TTS Flash","created":1784817207,"description":"Qwen-Audio-3.0-TTS Flash is Alibaba's fast, cost-efficient text-to-speech model, generating spoken audio from text via the DashScope Speech Synthesizer API.","context_length":0,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000015","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":["loongjohn","longanhuan_v3.6"],"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen-audio-3.0-tts-flash-20260723/endpoints"},"endpoints":["/api/v1/audio/speech"],"benchmarks":{"design_arena":[{"arena":"models","category":"audiorealism","elo":854,"win_rate":23,"rank":6}]}},{"id":"qwen/qwen-audio-3.0-tts-plus","canonical_slug":"qwen/qwen-audio-3.0-tts-plus-20260723","hugging_face_id":null,"name":"Qwen: Qwen-Audio-3.0-TTS Plus","created":1784817207,"description":"Qwen-Audio-3.0-TTS Plus is Alibaba's higher-quality text-to-speech model, generating spoken audio from text via the DashScope Speech Synthesizer API.","context_length":0,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00002","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":["longanlingxin","longanlufeng"],"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/qwen/qwen-audio-3.0-tts-plus-20260723/endpoints"},"endpoints":["/api/v1/audio/speech"]},{"id":"deepgram/aura-2","canonical_slug":"deepgram/aura-2-20260716","hugging_face_id":null,"name":"Deepgram: Aura-2","created":1784237167,"description":"Aura-2 is a multilingual text-to-speech model from Deepgram. It supports Deepgram’s canonical Aura-2 voice catalog for speech synthesis across multiple languages.","context_length":0,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00003","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":["aura-2-thalia-en","aura-2-agathe-fr","aura-2-agustina-es","aura-2-alvaro-es","aura-2-ama-ja","aura-2-amalthea-en","aura-2-andromeda-en","aura-2-antonia-es","aura-2-apollo-en","aura-2-aquila-es","aura-2-arcas-en","aura-2-aries-en","aura-2-asteria-en","aura-2-athena-en","aura-2-atlas-en","aura-2-aurelia-de","aura-2-aurora-en","aura-2-beatrix-nl","aura-2-callista-en","aura-2-carina-es","aura-2-celeste-es","aura-2-cesare-it","aura-2-cinzia-it","aura-2-cora-en","aura-2-cordelia-en","aura-2-cornelia-nl","aura-2-daphne-nl","aura-2-delia-en","aura-2-demetra-it","aura-2-diana-es","aura-2-dionisio-it","aura-2-draco-en","aura-2-ebisu-ja","aura-2-elara-de","aura-2-electra-en","aura-2-elio-it","aura-2-estrella-es","aura-2-fabian-de","aura-2-flavio-it","aura-2-fujin-ja","aura-2-gloria-es","aura-2-harmonia-en","aura-2-hector-fr","aura-2-helena-en","aura-2-hera-en","aura-2-hermes-en","aura-2-hestia-nl","aura-2-hyperion-en","aura-2-iris-en","aura-2-izanami-ja","aura-2-janus-en","aura-2-javier-es","aura-2-julius-de","aura-2-juno-en","aura-2-jupiter-en","aura-2-kara-de","aura-2-lara-de","aura-2-lars-nl","aura-2-leda-nl","aura-2-livia-it","aura-2-luciano-es","aura-2-luna-en","aura-2-maia-it","aura-2-mars-en","aura-2-melia-it","aura-2-minerva-en","aura-2-neptune-en","aura-2-nestor-es","aura-2-odysseus-en","aura-2-olivia-es","aura-2-ophelia-en","aura-2-orion-en","aura-2-orpheus-en","aura-2-pandora-en","aura-2-phoebe-en","aura-2-pluto-en","aura-2-rhea-nl","aura-2-roman-nl","aura-2-sander-nl","aura-2-saturn-en","aura-2-selena-es","aura-2-selene-en","aura-2-silvia-es","aura-2-sirio-es","aura-2-theia-en","aura-2-uzume-ja","aura-2-valerio-es","aura-2-vesta-en","aura-2-viktoria-de","aura-2-zeus-en"],"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepgram/aura-2-20260716/endpoints"},"endpoints":["/api/v1/audio/speech"]},{"id":"minimax/speech-2.8-hd","canonical_slug":"minimax/speech-2.8-hd-20260716","hugging_face_id":null,"name":"MiniMax: Speech 2.8 HD","created":1784164001,"description":"MiniMax Speech 2.8 HD is a text-to-speech model from MiniMax. It is suited for applications that generate spoken audio from text and accepts arbitrary MiniMax voice IDs.","context_length":0,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0001","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":["English_expressive_narrator","English_radiant_girl","English_magnetic_voiced_man","English_compelling_lady1","English_Aussie_Bloke","English_captivating_female1","English_Upbeat_Woman","English_Trustworth_Man","English_CalmWoman","English_UpsetGirl","English_Gentle-voiced_man","English_Whispering_girl","English_Diligent_Man","English_Graceful_Lady","English_ReservedYoungMan","English_PlayfulGirl","English_ManWithDeepVoice","English_MaturePartner","English_FriendlyPerson","English_MatureBoss","English_Debator","English_LovelyGirl","English_Steadymentor","English_Deep-VoicedGentleman","English_Wiselady","English_CaptivatingStoryteller","English_DecentYoungMan","English_SentimentalLady","English_ImposingManner","English_SadTeen","English_PassionateWarrior","English_WiseScholar","English_Soft-spokenGirl","English_SereneWoman","English_ConfidentWoman","English_PatientMan","English_Comedian","English_BossyLeader","English_Strong-WilledBoy","English_StressedLady","English_AssertiveQueen","English_AnimeCharacter","English_Jovialman","English_WhimsicalGirl","English_Kind-heartedGirl"],"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/minimax/speech-2.8-hd-20260716/endpoints"},"endpoints":["/api/v1/audio/speech"]},{"id":"minimax/speech-2.8-turbo","canonical_slug":"minimax/speech-2.8-turbo-20260716","hugging_face_id":null,"name":"MiniMax: Speech 2.8 Turbo","created":1784164000,"description":"MiniMax Speech 2.8 Turbo is a text-to-speech model from MiniMax. It is suited for applications that generate spoken audio from text and accepts arbitrary MiniMax voice IDs.","context_length":0,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00006","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":["English_expressive_narrator","English_radiant_girl","English_magnetic_voiced_man","English_compelling_lady1","English_Aussie_Bloke","English_captivating_female1","English_Upbeat_Woman","English_Trustworth_Man","English_CalmWoman","English_UpsetGirl","English_Gentle-voiced_man","English_Whispering_girl","English_Diligent_Man","English_Graceful_Lady","English_ReservedYoungMan","English_PlayfulGirl","English_ManWithDeepVoice","English_MaturePartner","English_FriendlyPerson","English_MatureBoss","English_Debator","English_LovelyGirl","English_Steadymentor","English_Deep-VoicedGentleman","English_Wiselady","English_CaptivatingStoryteller","English_DecentYoungMan","English_SentimentalLady","English_ImposingManner","English_SadTeen","English_PassionateWarrior","English_WiseScholar","English_Soft-spokenGirl","English_SereneWoman","English_ConfidentWoman","English_PatientMan","English_Comedian","English_BossyLeader","English_Strong-WilledBoy","English_StressedLady","English_AssertiveQueen","English_AnimeCharacter","English_Jovialman","English_WhimsicalGirl","English_Kind-heartedGirl"],"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/minimax/speech-2.8-turbo-20260716/endpoints"},"endpoints":["/api/v1/audio/speech"]},{"id":"microsoft/mai-voice-2","canonical_slug":"microsoft/mai-voice-2","hugging_face_id":null,"name":"Microsoft AI: MAI-Voice-2","created":1780425097,"description":"MAI-Voice-2 is an expressive text-to-speech model from Microsoft AI. It is suited for conversational assistants, media narration, accessibility, education, and other long-form voice applications. It supports 15 languages across 18...","context_length":0,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000022","completion":"0"},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":["en-US-Harper:MAI-Voice-2","es-MX-Valeria:MAI-Voice-2","fr-FR-Soleil:MAI-Voice-2","de-DE-Klaus:MAI-Voice-2"],"knowledge_cutoff":null,"expiration_date":"2026-12-31","links":{"details":"/api/v1/models/microsoft/mai-voice-2/endpoints"},"endpoints":["/api/v1/audio/speech"],"benchmarks":{"design_arena":[{"arena":"models","category":"audiorealism","elo":1208,"win_rate":61.1,"rank":1},{"arena":"models","category":"text-to-speech","elo":1160,"win_rate":52.6,"rank":2}]}},{"id":"x-ai/grok-voice-tts-1.0","canonical_slug":"x-ai/grok-voice-tts-1.0","hugging_face_id":null,"name":"SpaceXAI: Grok Voice TTS 1.0","created":1778805456,"description":"Grok Voice TTS 1.0 is a text-to-speech model from SpaceXAI. It converts text into spoken audio across 20+ languages with automatic language detection, and offers five built-in voices (Eve, Ara,...","context_length":15000,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":"0.000015","completion":"0"},"top_provider":{"context_length":15000,"max_completion_tokens":13500,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":["eve","ara","rex","sal","leo"],"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/x-ai/grok-voice-tts-1.0/endpoints"},"endpoints":["/api/v1/audio/speech"]},{"id":"google/gemini-3.1-flash-tts-preview","canonical_slug":"google/gemini-3.1-flash-tts-preview","hugging_face_id":null,"name":"Google: Gemini 3.1 Flash TTS Preview","created":1776999308,"description":"Gemini 3.1 Flash TTS Preview is a text-to-speech model from Google, and a substantial generational step up from Gemini 2.5 Flash TTS. It takes text input and produces audio output...","context_length":32768,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":"0.000001","completion":"0.00002"},"top_provider":{"context_length":32768,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{"temperature":null,"top_p":null},"supported_voices":["Zephyr","Puck","Charon","Kore","Fenrir","Leda","Orus","Aoede","Callirrhoe","Autonoe","Enceladus","Iapetus","Umbriel","Algieba","Despina","Erinome","Algenib","Rasalgethi","Laomedeia","Achernar","Alnilam","Schedar","Gacrux","Pulcherrima","Achird","Zubenelgenubi","Vindemiatrix","Sadachbia","Sadaltager","Sulafat"],"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemini-3.1-flash-tts-preview/endpoints"},"endpoints":["/api/v1/audio/speech"]},{"id":"canopylabs/orpheus-3b-0.1-ft","canonical_slug":"canopylabs/orpheus-3b-0.1-ft","hugging_face_id":null,"name":"Canopy Labs: Orpheus 3B","created":1776983168,"description":"Orpheus 3B is an English text-to-speech model from Canopy Labs, fine-tuned for natural prosody and expressive delivery. It offers 7 preset voices and is suited for narration, voice assistants, and...","context_length":4096,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000007","completion":"0"},"top_provider":{"context_length":4096,"max_completion_tokens":3686,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":["tara","leah","jess","leo","dan","mia","zac"],"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/canopylabs/orpheus-3b-0.1-ft/endpoints"},"endpoints":["/api/v1/audio/speech"]},{"id":"sesame/csm-1b","canonical_slug":"sesame/csm-1b","hugging_face_id":null,"name":"Sesame: CSM 1B","created":1776983168,"description":"CSM 1B is a conversational speech model from Sesame. It accepts text input and produces English speech output, with voice options spanning conversational and read-speech styles. At 1B parameters, it...","context_length":4096,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.000007","completion":"0"},"top_provider":{"context_length":4096,"max_completion_tokens":3686,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":["conversational_a","conversational_b","read_speech_a","read_speech_b","read_speech_c","read_speech_d","none"],"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/sesame/csm-1b/endpoints"},"endpoints":["/api/v1/audio/speech"]},{"id":"hexgrad/kokoro-82m","canonical_slug":"hexgrad/kokoro-82m","hugging_face_id":null,"name":"hexgrad: Kokoro 82M","created":1776983167,"description":"Kokoro 82M is a lightweight, open-weight text-to-speech model from hexgrad. It converts text to speech across 8 languages (American and British English, Spanish, French, Hindi, Italian, Japanese, Portuguese, and Chinese)...","context_length":4096,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.00000062","completion":"0"},"top_provider":{"context_length":4096,"max_completion_tokens":3686,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":["af_alloy","af_aoede","af_bella","af_heart","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_isabella","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"],"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/hexgrad/kokoro-82m/endpoints"},"endpoints":["/api/v1/audio/speech"]},{"id":"mistralai/voxtral-mini-tts-2603","canonical_slug":"mistralai/voxtral-mini-tts-2603","hugging_face_id":null,"name":"Mistral: Voxtral Mini TTS","created":1776571337,"description":"Voxtral Mini TTS is Mistral's text-to-speech model featuring zero-shot voice cloning and multilingual support. It converts text input into natural-sounding audio output.","context_length":4096,"architecture":{"modality":"text->speech","input_modalities":["text"],"output_modalities":["speech"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0.000016","completion":"0"},"top_provider":{"context_length":4096,"max_completion_tokens":3276,"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"supported_voices":["en_paul_sad","en_paul_neutral","en_paul_happy","en_paul_frustrated","en_paul_excited","en_paul_confident","en_paul_cheerful","en_paul_angry","gb_oliver_neutral","gb_oliver_sad","gb_oliver_excited","gb_oliver_curious","gb_oliver_confident","gb_oliver_cheerful","gb_oliver_angry","gb_jane_sarcasm","gb_jane_confused","gb_jane_shameful","gb_jane_sad","gb_jane_neutral","gb_jane_jealousy","gb_jane_frustrated","gb_jane_curious","gb_jane_confident","fr_marie_sad","fr_marie_neutral","fr_marie_happy","fr_marie_excited","fr_marie_curious","fr_marie_angry"],"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/mistralai/voxtral-mini-tts-2603/endpoints"},"endpoints":["/api/v1/audio/speech"]}],"total_count":38,"links":{"next":null}}