Voices

Find a voice

104 voices across 15 voice models from 15 providers, with what each model scored and the two ids that name a voice in a request.

Browse the roster

Live from the public catalog, GET /v1/models, rosters verified 2026-08-03. Filtering by language keeps the voices whose model is routable for it.

Voice
George - Warm, Captivating StorytellerElevenLabsmalewarmnarrationmature
elevenlabs:eleven_v3JBFqnCBsd6RMkjVDRZzb
Sarah - Mature, Reassuring, ConfidentElevenLabsfemaleprofessionalconfidentwarm
elevenlabs:eleven_v3EXAVITQu4vr4xnSDxMaL
Alice - Clear, Engaging EducatorElevenLabsfemaleclearengaginginformative
elevenlabs:eleven_v3Xb7hH8MSUJpSbSDYk0k2
Brian - Deep, Resonant and ComfortingElevenLabsmaledeepresonantcomforting
elevenlabs:eleven_v3nPczCjzI2devNBz1zQrb
Daniel - Steady BroadcasterElevenLabsmaleformalnewsauthoritative
elevenlabs:eleven_v3onwK4e9ZLuTAKqWW03F9
Matilda - Knowledgable, ProfessionalElevenLabsfemaleupbeatinformativeprofessional
elevenlabs:eleven_v3XrExE9yKIg1WjnnlVkGX
River - Relaxed, Neutral, InformativeElevenLabsneutralcalmrelaxedconversational
elevenlabs:eleven_v3SAz9YHcvj6GT2YYXdXww
Jessica - Playful, Bright, WarmElevenLabsfemaleplayfulbrightwarm
elevenlabs:eleven_v3cgSgspJ2msm6clMCkdW9
AoedeGooglefemalebreezyconversationalcalm
google-tts:gemini-3.1-flash-tts-previewAoede
KoreGooglefemalefirmconfident
google-tts:gemini-3.1-flash-tts-previewKore
ZephyrGooglefemalebrightenergetic
google-tts:gemini-3.1-flash-tts-previewZephyr
SulafatGooglefemalewarmfriendly
google-tts:gemini-3.1-flash-tts-previewSulafat
CharonGooglemaleinformativedeepsteady
google-tts:gemini-3.1-flash-tts-previewCharon
PuckGooglemaleupbeatexpressiveenergetic
google-tts:gemini-3.1-flash-tts-previewPuck
EnceladusGooglemalebreathysoftintimate
google-tts:gemini-3.1-flash-tts-previewEnceladus
ThaliaDeepgramfemaleclearconfidentenergetic
deepgram:aura-2aura-2-thalia-en
AsteriaDeepgramfemaleclearconfidentknowledgeable
deepgram:aura-2aura-2-asteria-en
AthenaDeepgramfemalecalmsmoothprofessional
deepgram:aura-2aura-2-athena-en
AndromedaDeepgramfemalecasualexpressivecomfortable
deepgram:aura-2aura-2-andromeda-en
OrionDeepgrammaleapproachablecalmpolite
deepgram:aura-2aura-2-orion-en
OrpheusDeepgrammaleprofessionaltrustworthynarration
deepgram:aura-2aura-2-orpheus-en
ZeusDeepgrammaledeeptrustworthysmooth
deepgram:aura-2aura-2-zeus-en
DracoDeepgrammalewarmbaritonebritish
deepgram:aura-2aura-2-draco-en
TessaCartesiafemaleconversationalfriendlyemotive
cartesia:sonic-3.56ccbfb76-1fc6-48f7-b71d-91ac6298247b

104 voices

What each one scored

Naturalness is measured per language, not inferred from English — the model that wins one study routinely loses another. Every figure is the board's own.

#ModelNaturalnessarena EloSynthenglish board p50Cost$ / M chars
1
gemini-3.1-flash-tts-previewgoogle-tts:gemini-3.1-flash-tts-preview
1591978ms~$33.3
2
eleven_v3elevenlabs:eleven_v3
1590481ms$100.0
3
aura-2deepgram:aura-2
1584125ms$30.0
4
sonic-3.5cartesia:sonic-3.5
1574121ms$50.0
5
simba-3.2speechify:simba-3.2
1573345ms$10.0
6
tts-rt-v1soniox:tts-rt-v1
1569362ms~$13.0
7
s2.1-probenchmark only — not routable
~1566185ms$15.0
8
inworld-tts-2inworld:inworld-tts-2
1561116ms$25.0
9
lightning_v3.1smallest:lightning_v3.1
1544173ms$25.0
10
palabra-tts-v1benchmark only — not routable
~152072ms$30.0
11
grok-ttsxai:tts
1495272ms$15.0
12
defaultgradium:default
1448244ms$57.8
13
speech-2.8-hdminimax:speech-2.8-hd
1431294ms$100.0
14
arcanav3rime:arcanav3
1429238ms$40.0
15
gpt-4o-mini-ttsopenai:gpt-4o-mini-tts
1424691ms~$20.0
16
octave-2hume:octave-2
1377448ms$100.0
17
qwen3-tts-flashalibaba:qwen3-tts-flash
1310472ms$10.0

Naturalness / arena Elo. Higher is better. Blind A/B votes, field mean 1500. Latency and price are the English board’s, by model — a model measured only in this study carries neither.

Voice models and language coverage

Which model each voice belongs to, and the languages the router will select it for.

ModelVoices
sonic-3.5cartesia:sonic-3.5
7
enardeesfilfrhinbtate
eleven_v3elevenlabs:eleven_v3
8
enardeesfilfrhinbta
speech-2.8-hdminimax:speech-2.8-hd
6
endeesfilfrhinb
gpt-4o-mini-ttsopenai:gpt-4o-mini-tts
8
endeesfilfrnb
gemini-3.1-flash-tts-previewgoogle-tts:gemini-3.1-flash-tts-preview
7
enfilhinbtate
inworld-tts-2inworld:inworld-tts-2
7
enardeesfilfr
grok-ttsxai:tts
5
enardeesfilfr
aura-2deepgram:aura-2
8
endeesfr
arcanav3rime:arcanav3
7
endeesfr
lightning_v3.1smallest:lightning_v3.1
7
endeesfr
octave-2hume:octave-2
7
endeesfr
qwen3-tts-flashalibaba:qwen3-tts-flash
7
endeesfr
tts-rt-v1soniox:tts-rt-v1
7
endeesfr
defaultgradium:default
8
endefr
simba-3.2speechify:simba-3.2
5
en
palabra-tts-v1benchmark only — not routable
no languages declared
s2.1-probenchmark only — not routable
no languages declared

Take one to the API

A voice is two strings: the model id you send as model, and the voice’s own id you send as voice. Both are in the table above, and the speech endpoint is the OpenAI-compatible one your client already calls.

curl https://api.speko.ai/v1/audio/speech \
  -H "Authorization: Bearer $SPEKO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google-tts:gemini-3.1-flash-tts-preview",
    "voice": "Aoede",
    "input": "Hello from Speko."
  }'

Leave model as auto and the router picks the voice model for you, per language and per objective, from the same measurements the boards on this page publish.