Voice library
60,732 ready-made voices from three speech providers, each with the voice ID you pass to the API. Filter by language, gender and source, play a preview, then open the model page with that voice already selected.
94 languages across the three providers. The catalog is refreshed daily; last refresh 2026-10-29. Page last updated 2026-10-29
Pass the ID as voice_id to any ElevenLabs TTS model (eleven-tts-v3, eleven-tts-multilingual, eleven-tts-flash and the rest). Voice library entries work by ID directly; there is nothing to add to an account first.
UgBBYS2sOqTuMpoF3BR0A casual, young-adult speaking in a natural manner. Perfect for Conversational AI.
IRHApOXLvnW57QJPQH2PA tough hero, weathered by years of experience. American accent.
zgqefOY5FPQ3bB7OZTVRNiraj is the pen name of a veteran Indian actor. The base and variations of this voice make it great for narrative work, documentaries, and social media.
EkK5I93UQWFDigLMpZcXA slightly husky and bassy voice with a standard American accent. Modulated, controlled, and direct and perfect for audiobooks, captivating narrations, or storytelling, or other professional voiceover work.
FZkK3TvQ0pjyDmT8fzIWA vibrant AI voice crafted for content creators, influencers, and digital storytellers. Bunty’s natural, expressive tone makes videos feel relatable and compelling, perfect for YouTube shorts, Instagram reels, and TikTok trends. His engaging style enhances storytelling, promotions, and entertainment content, keeping audiences hooked. Designed for creators looking to boost engagement and authenticity in Hindi-language content, Bunty delivers a smooth and dynamic performance.
uju3wxzG5OhpWcoi3SMyA confident and expressive narrator across multiple genres. Warm bass tones and crisp high-end clarity deliver an articulate, intelligent voice suited for commercials, explainers, educational narrations and storytelling.
wBXNqKUATyqu0RtYt25iA middle aged American male voice with a rich tone, good for a radio announcer.
NFG5qt843uXKj4pFvR7CA middle aged 'Brit' with a velvety laid back, late night talk show host timbre.
ZthjuvLPty3kTMaNKVKbConfident, reliable, credible narrator. A resolute voice that you can trust.
tnSpp4vdxKPjI9w0GnoVupbeat
G17SuINrv2H9FC6nvetnBritish male narrator, English, well-spoken, gentle and trustworthy voice. Great for audiobooks, podcasts and voiceovers.
Nh2zY9kknu6z4pZy6FhDYoung Spanish-Castillian male with a confident tone. Works well for Storytelling.
yl2ZDV1MzN4HbQJbMihGAn upbeat and pleasant male voice. Great for Youtube, shorts and social media.
56AoDkrOh6qfVPDXZ7PtA confident female podcaster with plethora of experience in the music industry.
1qEiC6qsybMkmnNdVMbKMonika Sogam is already a pretty loved voice on ElevenLabs in the English Indian category. Now it is available in Hindi too. This is a perfect voice for social media, audiobooks, and any type of conversational audio you might be looking for.
r1KmysJdVYZjJCm4mL3bThe old Jessica default voice you know and love! Playful, Bright, Warm, youthful, and conversational. Perfect for your project. Voiced by real voice actor Lorin Zackular.
l1zE9xgNpUTaQCZzpNJaAdult male voice, serious tone, ideal for narrations.
kPzsL2i3teMYv0FxEYQ6A young, vibrant female voice that is perfect for celebrity news, hot topics, and fun conversation. Great for YouTube channels, informative videos, how-to's, and more!
7b9mYhmnp0y2qSH1FnBLBunty’s voice is full of charm, wit, and best-friend energy—ideal for funny reels, roast-style rants, relatable meme content, and banter-led storytelling. With a naturally desi tone and perfect comic timing, his voice feels like your everyday buddy pulling your leg, making it perfect for creators, meme pages, and short-form comedy content on social media platforms.
Z3R5wn05IrDiVCyEkUrKA young, mature female narrator with a mysterious and emotive tone, perfect for fantasy, romance, urban fantasy, and wellness.
1SM7GgM6IMuvQlz2BwM3casual
RWiGLY9uXI70QL540WNdA young Indonesian man with a fiery enthusiasm, to convey messages more clearly.
lxYfHSkYm1EzQzGhdbfcA credited VoiceOver actor, now cloned. Confident, Conversational.
MF4J4IDTRo0AxOO4dpFRDevi is the pen name of a young Indian female artist with clear Hindi instructions. She originally comes from Rajasthan, so she has a clear Hindi diction and hence a beautiful voice for educational, social media, and audiobook content.
9F4C8ztpNUmXkdDDbz3JAn upbeat and modulate voice. Great for shorts and social media.
MFZUKuGQUsGJPQjTS4wCA warm, trustworthy American voice with a mature and grounded tone. Ideal for narration and commercials. It carries an intelligent and calm presence, making it perfect for delivering messages with clarity.
alFofuDn3cOwyoz1i44TAdult American Male Voice. Calming, Deep, Warm. Perfect for stories.
goT3UYdM9bhm0n2lmKQxA deep, low, seductive strong British man.
3EuKHIEZbSzrHGNmdYsxMiddle-aged Russian male with a confident tone. Great for Social media.
wyWA56cQNU2KqUW4eCsIBritish man with power who shows nuance and humor -- wonderful narrator voice.
s3TPKV1kjDlVtZbl4KshAdam is a male voice, 20s–30s, blends clarity, and confident expression. Ideal for creators and brands who want their content to feel real, relatable, and human. Trained across multiple formats including storytelling, ads, social media, tutorials, and casual dialogue, Adam adapts seamlessly to your tone. Whether guiding, selling, or narrating, Adam builds trust, relatability, and connection from the very first word. Friendly, grounded, expressive -ready to elevate your content
36rVQA1AOIPwpA3Hg1tCA young energetic male voice. Great for social media, shorts and video games.
EiNlNiXeDU1pqqOPrYMOMiddle aged American male with a very deep voice. Perfect for audiobooks.
iiidtqDt9FBdT1vfBluAMature adult male, factual, clear, conversational baritone. Also great for these categories: characters, educational, advertisement, social media, conversational, and entertainment, too.
NNl6r8mD7vthiJatiJt1An adult British Male Storyteller. Expressive, articulate, and engaging!
zT03pEAEi0VHKciJODfnThis voice has the familiar warmth and approachability of a regular Indian speaker, yet it carries a professionalism that makes it versatile for a range of applications. It's clear and articulate enough to engage audiences on social media, provide guidance through customer care bots, and serve in various other communication roles. Its authentic Indian tone adds a layer of relatability without compromising on clarity or effectiveness, making it an excellent choice for connecting with audiences.
e5WNhrdI30aXpS2RSGm1A middle age American voice which captures the tone and pace of your favorite mystery or suspense novel. Great for audiobooks and True Crime content.
gJEfHTTiifXEDmO687lCFragrant velvet voice. A tempting combination of low shades with hot notes will emphasize the depth and richness of your reel, shorts or audiobook.
j9jfwdrw7BRfcR43QohkProfessional, calm, well spoken British narrator full of intrigue and wonder. Suitable for Nature, Science, Mystery & History documentaries or audio books & narration projects that need a smooth & velvety tone.
3AMU7jXQuQa3oRvRqUmbViraj delivers a richly modulated and emotionally expressive tone—ideal for audiobooks and storytelling with vivid dialogue. His voice naturally shifts between characters, making it perfect for fiction, romance, thrillers, and mythology. This profile is specially tuned for dialogue-heavy narration. With over 1.5 billion characters across his other profiles, Viraj is already one of ElevenLabs’ most celebrated voices. Great fit for Audible, PocketFM, Spotify, KukuFM, & other longform platforms.
7qBNUtXRGP0jPi0H4r8kBunty delivers an energetic, youthful, and friendly delivery that feels approachable and upbeat during e-commerce interactions. His tone keeps conversations light, helpful, and efficient. Ideal for order support, delivery updates, return and refund queries, onboarding calls, and customer assistance. Well-suited for e-commerce platforms, D2C brands, online marketplaces, and shopping apps that want customer support to feel fast, friendly, and relatable.
HJmys3t5KLr6DUWl0kSeYoung relaxed male voice. Great for Storytelling.
dtSEyYGNJqjrtBArPCVZA commanding, versatile male voice built for impact and authority. Perfect for TikTok & YouTube story narrations, viral social media content, celebrity news updates, political recaps, true crime stories, politics, reaction videos, and explainer shorts. Ideal for audiobooks, cinematic documentaries, history & science narration, fantasy storytelling, infomercial narration, motivational speeches, and inspirational content. His clarity makes Titan a strong fit for corporate training, UGC, and more!
H5xTcsAIeS5RAykjz57aMiddle aged European (polish) Male with a stead & calm voice. Great for documentaries, audiobook, ads.
auq43ws1oslv0tO4BDa7Updated for even higher quality. A British man with a velvety, laid-back, late-night talk show warmth. Deep, smooth, studio-quality delivery for long or short-form retention and high engagement across socials, podcasts, adverts, and professional video production. I'm also your perfect choice for narration and audio books. More cinematic, more intimate, more engaging.
dlGxemPxFMTY7iXagmOjMiddle aged casual male voice. Ideal for narrations.
XjLkpWUlnhS8i7gGz3lZA clear and crisp middle age professional American voice that is in the style of Broadcast news presenters. Great for the reader app for long form content.
P1bg08DkjqiVEzOn76yGViraj’s voice brings depth and intrigue, perfect for suspense and horror storytelling. With a slow, deliberate pace and a rich, breathy tone, his delivery creates a haunting, immersive atmosphere. Ideal for chilling narratives, his booming presence draws listeners into a world of mystery and tension.
All three providers run on the same endpoint, POST https://api.apimodels.app/v1/audio/generations, with the same API key. Only the field that carries the voice differs: voice_id for MiniMax and ElevenLabs, reference_id for Fish Audio. The call returns a task ID; poll GET /v1/audio/generations?task_id=… or pass callback_url to be notified.
voice_id · minimax-speech-2.8-turbo / minimax-speech-2.8-hdcurl -X POST https://api.apimodels.app/v1/audio/generations \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "minimax-speech-2.8-turbo",
"text": "Welcome back. Here is today's summary.",
"voice_id": "Arnold"
}'voice_id · eleven-tts-v3 / eleven-tts-multilingualcurl -X POST https://api.apimodels.app/v1/audio/generations \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "eleven-tts-v3",
"text": "Welcome back. Here is today's summary.",
"voice_id": "EXAVITQu4vr4xnSDxMaL"
}'reference_id · fish-s2.1-pro / fish-drama-3curl -X POST https://api.apimodels.app/v1/audio/generations \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "fish-s2.1-pro",
"text": "Welcome back. Here is today's summary.",
"reference_id": "297a6fd278df47c3b9da9bfdf55ac89a"
}'Full parameters (speed, format, emotion and more): Audio API docs · Fish Audio · Voice cloning and design
Three short lists you can copy from straight away: the official ElevenLabs presets that every account has, the most-used Fish Audio licensed voices, and a dozen MiniMax English voices. The tabs above hold the full lists.
| Name | voice_id | Language | Voice |
|---|---|---|---|
| Adam - Dominant, Firm | pNInz6obpgDQGcFmaJgB | English | Male · American |
| Alice - Clear, Engaging Educator | Xb7hH8MSUJpSbSDYk0k2 | English | Female · British |
| Bella - Professional, Bright, Warm | hpp4J3VqNfWAUOO0d1Us | English | Female · American |
| Bill - Wise, Mature, Balanced | pqHfZKP75CvOlQylNhV4 | English | Male · American |
| Brian - Deep, Resonant and Comforting | nPczCjzI2devNBz1zQrb | English | Male · American |
| Callum - Husky Trickster | N2lVS1w4EtoT3dr4eOWO | English | Male · American |
| Charlie - Deep, Confident, Energetic | IKne3meq5aSn9XLyUdCD | English | Male · Australian |
| Chris - Charming, Down-to-Earth | iP95p4xoKVk53GoZ742B | English | Male · American |
| Daniel - Steady Broadcaster | onwK4e9ZLuTAKqWW03F9 | English | Male · British |
| Eric - Smooth, Trustworthy | cjVigY5qzO86Huf0OWal | English | Male · American |
| George - Warm, Captivating Storyteller | JBFqnCBsd6RMkjVDRZzb | English | Male · British |
| Harry - Fierce Warrior | SOYHLrjzK2X1ezoPC6cr | English | Male · American |
| Jessica - Playful, Bright, Warm | cgSgspJ2msm6clMCkdW9 | English | Female · American |
| Laura - Enthusiast, Quirky Attitude | FGY2WhTYpPnrIDTdsKH5 | English | Female · American |
| Liam - Energetic, Social Media Creator | TX3LPaxmHKxFdv7VOQHJ | English | Male · American |
| Lily - Velvety Actress | pFZP5JQG7iQjIQuC4Bku | English | Female · British |
| Matilda - Knowledgable, Professional | XrExE9yKIg1WjnnlVkGX | English | Female · American |
| River - Relaxed, Neutral, Informative | SAz9YHcvj6GT2YYXdXww | English | Neutral · American |
| Roger - Laid-Back, Casual, Resonant | CwhRBWXzGAHq8TQ4Fs17 | English | Male · American |
| Sarah - Mature, Reassuring, Confident | EXAVITQu4vr4xnSDxMaL | English | Female · American |
| Will - Relaxed Optimist | bIHbv24MWmeRgasZH58o | English | Male · American |
| Name | voice_id | Language | Voice |
|---|---|---|---|
| Arnold | Arnold | English | — |
| Assertive Queen | English_AssertiveQueen | English | Female |
| Attractive Girl | Attractive_Girl | English | Female |
| Aussie Bloke | English_Aussie_Bloke | English | Male |
| Bossy Lady | English_MatureBoss | English | Female |
| Bossy Leader | English_BossyLeader | English | — |
| Calm Woman | English_CalmWoman | English | Female |
| Captivating Female | English_captivating_female1 | English | Female |
| Captivating Storyteller | English_CaptivatingStoryteller | English | — |
| Charming Lady | Charming_Lady | English | Female |
| Charming Santa | Charming_Santa | English | — |
| Comedian | English_Comedian | English | — |
| Name | reference_id | Language |
|---|---|---|
| さとる Satoru | 297a6fd278df47c3b9da9bfdf55ac89a | Japanese |
| じん Jin | d738c70d206149e69f8e3b6fc8af9d96 | Japanese |
| きょうこ Kyoko | b2d9d8db057042688a5e318b8f405bc2 | Japanese |
| あかり Akari | 97eda32449cf443bbc4b8782853ca554 | Japanese |
| 美咲 Misaki | 35c8e5ae5239435f8d9c26c86802b86d | Japanese |
| しおり Shiori | 5da7f24e9e274f91b2b677669c818ce9 | Japanese |
| まこと Makoto | 59a78821a8924989b70d2a63d588e8eb | Japanese |
| ПРОФЕССОР МОРИАРТИ | 0e16ac9230bd4dd5b2eba5394a9379b9 | Russian |
| Uncle Roger | 27d552ba597a4d54b4ea5c7c3962d3dd | English |
| SleepyCatHey? WHAT | 0d472141c45549ff993bb70198a3a89e | English |
| 스토리텔러 20대 후반 | 1522b08ff8824100b4df795a4d149206 | Korean |
| BRIAN - Voz Tranquila y Reflexiva | f40c5dc43e7e4e3ba641b6e8b53ad7c2 | Spanish |
Everything on this page comes from a public endpoint you can call yourself, without an API key, to build a voice picker into your own product or keep a local copy of the IDs.
# Public, no API key. CORS enabled, cached for 5 minutes.
curl "https://api.apimodels.app/v1/voices/catalog?provider=elevenlabs&language=en&gender=female&page_size=20"
# Counts per provider, source and language
curl "https://api.apimodels.app/v1/voices/catalog/manifest"| Parameter | Values |
|---|---|
| provider | minimax · elevenlabs · fish |
| source | minimax: system · elevenlabs: premade, professional, library · fish: licensed, community |
| language | ISO 639-1 code such as en, ja or es; Cantonese is yue |
| gender | female · male · neutral (MiniMax and ElevenLabs; MiniMax voices are tagged only where the name makes it clear) |
| q | Matches name, ID, description, accent and use case |
| sort | popular (default) · name |
| page / page_size | Pages start at 1; up to 100 voices per page, 50 by default |
A response, trimmed to one voice:
{
"code": 200,
"msg": "success",
"data": {
"total": 20680,
"page": 1,
"page_size": 1,
"has_more": true,
"items": [
{
"id": "UgBBYS2sOqTuMpoF3BR0",
"name": "Mark - Natural Conversations",
"provider": "elevenlabs",
"source": "library",
"languages": [
"en",
"fil",
"it",
"fr",
"hu",
"hi",
"hr",
"ko",
"sk",
"uk",
"sv",
"ta",
"ru",
"ar",
"ms",
"zh",
"ro",
"id",
"vi",
"pl",
"no",
"de",
"el",
"nl",
"cs",
"es",
"pt",
"tr",
"da"
],
"gender": "male",
"age": "young",
"accent": "american",
"description": "A casual, young-adult speaking in a natural manner. Perfect for Conversational AI.",
"use_case": "conversational",
"preview_url": "https://storage.googleapis.com/eleven-public-prod/database/workspace/f94e260200764678babc807b935bfb0b/voices/UgBBYS2sOqTuMpoF3BR0/0Oc7jiXwWN9kRTXfQsmw.mp3",
"uses": 4171141
}
]
}
}Responses carry Access-Control-Allow-Origin: *, so a browser can call the endpoint directly. Results are cached for five minutes and the catalog is rebuilt once a day.
System voices: the English and multilingual voices on MiniMax's current official list, plus older Mandarin voices that still synthesize. MiniMax publishes no preview audio for them, so try a voice on the model page.
Official presets (21), professional voices (131) and the shared voice library (20,528), which holds voices ElevenLabs users have published for others to use. Every one works by ID on all ElevenLabs TTS models.
Licensed voices (235) are Fish Audio's own catalogue, listed in full. Community voices (39,442) are user uploads, gathered from the most-used, highest-rated and newest voices in each language; voices removed for copyright claims are left out.
Community voices are uploaded by other users, and some imitate real people or well-known characters. Being listed here is not a licence: check that you have the commercial and likeness rights before publishing anything made with one.
Need a voice that is yours alone? Clone one from a short sample or design one from a description; Fish Audio S2.1 Pro includes 20 voice clones at no cost.
Open the ElevenLabs tab above, filter by language, gender or source, and press Copy ID on any card. The ID is the same string ElevenLabs itself uses, so it works as voice_id on every ElevenLabs TTS model here (eleven-tts-v3, eleven-tts-multilingual, eleven-tts-flash and the rest). Voices from the shared voice library work by ID directly; there is nothing to add to an account first.
The MiniMax tab lists all 375 system voices: the English and multilingual voices on MiniMax's current official list, plus older Mandarin IDs such as male-qn-qingse that still synthesize. Pass the ID as voice_id to minimax-speech-2.8-turbo, minimax-speech-2.8-hd or any other MiniMax speech model. MiniMax publishes no preview audio for system voices, so each card carries a Try it button that opens the model page with that voice selected.
Copy the 32-character ID and send it as reference_id to fish-s2.1-pro or fish-drama-3 (voice_id is accepted as an alias). Licensed voices are Fish Audio's own catalogue and are billed at a higher rate: twice the standard rate on S2.1 Pro and 2.5 times on Drama 3. Community voices and your own clones are billed at the normal rate.
Fish Audio community voices are uploaded by other users, and some imitate real people or well-known characters; voices in the ElevenLabs voice library are published by their creators on ElevenLabs and follow ElevenLabs' terms. Being listed here is not a licence. Before you publish or sell anything made with one of these voices, make sure you have the right to use that voice and likeness. For commercial work, licensed voices and official presets are the safer choice.
Yes. GET https://api.apimodels.app/v1/voices/catalog returns the same data as JSON with no API key: filter with provider, source, language, gender and q, sort by popular or name, and page through with page and page_size (up to 100 per page). /v1/voices/catalog/manifest returns the counts per provider, source and language. The catalog is rebuilt once a day.
No. Speech is billed at the model's own rate (per 1,000 characters on most models, per 1,000 UTF-8 bytes on Fish Audio models) whichever preset or library voice you pick. The one exception is Fish Audio's licensed voices: twice the standard rate on S2.1 Pro and 2.5 times on Drama 3. Failed requests are not billed.
MiniMax publishes no sample audio for its system voices, and a few library entries have none either. Try it opens the model page with the voice already selected; sign in and generate a short line to hear it.