AiRecMark/AI Tools/Audio & Music/Chatterbox
INDEX / AUDIO_SPEECH / CHATTERBOX
github.com verified
CH

Chatterbox

Verified Benchmark

SoTA open source TTS with emotion control from Resemble AI

FREE PRICING SCORE 82.6/100 4 RECORDED FEATURES UPDATED 2026-09-17
AiRecMark Score
82.6 /100
trending_up v2-5dim
workspace_premium #9 in Voice & Music AI
Launch Console north_east
Output Quality record_voice_over
83%

Quality & reliability of primary audio output.

Feature Depth bolt
76%

SoTA zero-shot TTS

Usability fingerprint
72%

Onboarding & editor ergonomics.

Entry Price payments
Free open source (MIT)

Free open source (MIT) · community edition on GitHub

Scoring Vectors

Deterministic evaluation across the AiRecMark five-dimension rubric (v2-5dim)

SNAPSHOT 2026-09-17
sentiment_satisfied Output Quality & Reliability (Weighted 25%) 83%
format_quote Feature Depth & Integrations (Weighted 20%) 76%
noise_aware Onboarding & Usability (Weighted 15%) 72%
auto_stories Runtime Performance & Latency (Weighted 20%) 84%
graphic_eq Price-to-Value Efficiency (Weighted 20%) 95%
PACKET TRANSIT DISTRIBUTION (PING JITTER) 5-dim spread ±11.5 pts (5-dim spread)
40ms 65ms (Median) 75ms (Flash TTFT) 120ms
graphic_eq ARCHIVE RECORD
v2-5dim
QUALITY DIM 83%
FEATURES DIM 76%
VALUE DIM 95%
terminal quickstart.py 
# Chatterbox — official documentation

"https://github.com"


# Pricing source (T0): https://github.com/resemble-ai/chatterbox

# Entry tier: Free open source (MIT) · community edition on GitHub (checked 2026-09-17)

# Rubric: v2-5dim · recorded features: 4

Quantitative Technical Specification

Core architectural subsystems in production release v2.5

speed

SoTA zero-shot TTS

Competitive open source text-to-speech quality.

Capability T0 Verified
mic_double

Emotion exaggeration control

Dial emotion intensity in generated speech.

Capability T0 Verified
support_agent

0.5B Llama backbone

Llama-based architecture underlying generation.

Capability T0 Verified
surround_sound

Built-in watermarking

Output watermarking for responsible use.

Capability T0 Verified

Direct Peer Matrix: Voice Synthesis & Conversational Engines

Standardized comparative evaluation using normalized 1,000-character test payloads

Benchmarks Updated 2026-09-14
Model & Provider AiRecMark Score Pricing Base Performance (rubric) Languages Prosody Fidelity
Chatterbox Leader 82.6 Free open source (MIT) 84/100 — 83%
ElevenLabs 95.4 Usage API / Tiered — — —
PlayHT 89.2 Freemium — — —
Cartesia 85.8 $5/mo — — —
Adobe Podcast 85.6 $0/mo — — —

Commercial Tiers & Compute Allocation

Transparent character pools, concurrent socket capacities, and API rate limits

Pro Popular
Custom /mo

Free open source (MIT) · community edition on GitHub

  • check SoTA zero-shot TTS
  • check Emotion exaggeration control
  • check 0.5B Llama backbone
Enterprise
Custom SLA terms

Dedicated infrastructure, security review, and compliance support.

  • check SSO / SAML & audit controls
  • check Dedicated support channel
  • check Custom quota & SLA
verified_user
AIrecmark Analyst Consensus Verdict SCORING MODEL: v2-5dim

Chatterbox stands out for mIT license. SoTA open source TTS with emotion control from Resemble AI anchors its proposition, and AiRecMark's five-dimension audit lands it at 82.6/100 — a pragmatic default for developers Wanting Controllable Open TTS.

Lead Evaluator: AiRecMark Audio Analyst Group
ARCHIVE SNAPSHOT: 2026-09-17 · github.com