Fish Audio
Next-generation expressive AI voice synthesis, neural TTS, and voice cloning platform (2 benchmarked capabilities: Text to speech, Audio transcription)
Product node overview & trust baseline
Operator provenance, privacy baseline and site-wide pricing belong directly to the product node and are inherited across linked task edgesFish Audio, operated by Fish Audio (Hanabi AI Inc.) (Delaware, USA) under a "Free tier + subscription" model, has 2 published task assessments on RealTest (Text to speech 94/100, Audio transcription 87/100). In text to speech, fish Audio delivers high-fidelity 44.1kHz MP3 speech synthesis powered by Drama 3 in 4.19 seconds on the standard 497-character benchmark with free native export. In audio transcription, fish Audio offers guest-accessible online speech-to-text, achieving 100% keyword and verification token recall on the standard anchor with native TXT export.
Delaware, USA · Creators of open-source Fish Speech, operating continuously
Provenance baseline: 18/20 · Leading speech AI research team behind open-source Fish Speech with transparent benchmarks and verified entity.
Offers Free tier (8K credits/mo, ~7 mins); paid subscriptions include Plus ($15/mo, $66/yr introductory annual) and Pro ($100/mo, $450/yr introductory annual).
Pricing transparency baseline: 34/35 · Cancellation:
Cloned voices and generated audio stored in user console with full deletion and privacy management
Google Analytics · Stripe · Cloudflare
Product-level pricing & rules baseline
Verified plans, billing periods and cancellation terms owned by this product node; task-specific credit costs and free export limits are detailed per capability edge belowSite-wide TTS, Voice Design, and voice cloning plans on Fish Audio · 2026-11-12
Realistic AI voice synthesis, 3 public voice slots, enhanced voice cloning, no credit card required;500 chars/conv limit, personal non-commercial use only
15,000 chars/conv, unlimited public + 10 private slots, priority queue, Voice Design, commercial rights
15,000 chars/conv, unlimited public + 10 private slots, priority queue, Voice Design, commercial rights
30,000 chars/conv, 3 team seats, unlimited voice slots, 5 pro slots, 7-day refund guarantee
30,000 chars/conv, 3 team seats, unlimited voice slots, 5 pro slots, 7-day refund guarantee
5 plan / billing-period records, all listed; — means that period is not recorded.
Offers Free tier (8K credits/mo, ~7 mins); paid subscriptions include Plus ($15/mo, $66/yr introductory annual) and Pro ($100/mo, $450/yr introductory annual).
Cancellation, sources & verification record
Cancellation and refund terms unverified
Fish Audio Official Homepage & Studio ↗ · 2026-11-12 Capture 1 ↗
Fish Audio Official Pricing & Plans ↗ · 2026-11-12 Capture 1 ↗
Archived official pricing sources: Fish Audio Official Homepage & Studio (2026-11-12) [text snapshot ↗] · Fish Audio Official Pricing & Plans (2026-11-12) [text snapshot ↗]
Capability map & linked task edges
Whenever a capability passes fixed-fixture testing, an edge is automatically linked between this product node and the task topic for horizontal comparison.
| Linked task edge | Score | Assessment · historical test | Test scope & delivery | Inspect capability / follow edge |
|---|---|---|---|---|
| Audio transcription | 87/100 | Fish Audio offers guest-accessible online speech-to-text, achieving 100% keyword and verification token recall on the standard anchor with native TXT export. | TXT · Output attached Historical test · 2026-11-15 Guest flow · 38.86s clean spoken English audio master (with verification token & numbers, 608 KB) · Output attached | |
| Text to speech | 94/100 | Fish Audio delivers high-fidelity 44.1kHz MP3 speech synthesis powered by Drama 3 in 4.19 seconds on the standard 497-character benchmark with free native export. | MP3 · Output attached Historical test · 2026-11-15 Signed-in flow; paid tier not standardized · 68-word standard spoken English text script (with currency, time & verification token, 452 chars) · Output attached |
Tested task edges (with scores and native artifacts) are strictly separated from discovered untested capabilities (unscored).
Peer product comparison across shared task edges
Matched by overlapping tested task edges; compare site-wide billing models alongside per-task benchmark scoresFree tier provides 10 robotic voices and up to 1.5x speed; Premium tier costs $29/month or $139 billed yearly (approx. $11.58/mo, 60% savings) with 1000+ natural voices, 60+ languages, and voice typing.
- Audio transcription:Fish Audio 87/100 vs Speechify 86/100
- Text to speech:Fish Audio 94/100 vs Speechify 92/100
Free tier supports 500MB uploads (watermarked, 720p cap, 14-day retention, 10 credits/mo); Pro plan is $12/mo or $108/yr ($9/mo equivalent, saves 25%) with no watermark, high-quality compression, 4K exports, and unlimited storage.
- Text to speech:Fish Audio 94/100 vs Clideo 87/100
Free tier includes 10 credits (watermarked, up to 4 min, 720p); Pro plan is $24/mo or $192/yr ($16/mo equivalent, saves 33%); Business plan is $64/mo or $600/yr ($50/mo equivalent); Enterprise tier offers custom quotas.
- Text to speech:Fish Audio 94/100 vs Kapwing 95/100
Includes a 30-minute free trial without credit card; Pay As You Go credits start at $11 (valid 2 years); monthly subscriptions at $11/mo (10h), $28/mo (30h), and $90/mo (100h); annual subscriptions at $110/yr, $300/yr, and $900/yr; unused credits roll over up to 3x.
- Audio transcription:Fish Audio 87/100 vs Cleanvoice AI 70/100
Linked capability test: Audio transcription
2026-11-15 · Native output attached. Findings cover the recorded fixture and conditions; paid specifications may be untested.
Verified native export & same-run screenshot evidence
Open native exported file (TXT · Output attached) ↗Task quality
Word accuracy 79.4% · Keyword recall 100% · Verification token Pass · Audio duration 38.9s
Detailed facts & historical record
- Measured fixture results
Word accuracy: 79.4% · Keyword recall: 100% · Verification token: Pass · Audio duration: 38.9s
- Fixture findings
100% keyword recall (10/10) with exact numerical and token retention, exporting native 0.5 KB TXT deliverable.
- Original historical observation
Fully retained RealTestTranscribeVerified2026 token and all financial figures with 100% recall
- Suitable uses · historical assessment
Not verified
- Result & output evidence
Delivery capabilities
TXT · Output attached · No watermark in test
Detailed facts & historical record
- Recorded export specifications
TXT · Output attached · No watermark in test
- Historical specification note · not an official maximum
Native TXT text (0.5 KB, 64 words, with speaker labels)
- Watermark observation
No watermark
- Batch & API
Not verified
- Recorded free-tier dimensions
Not verified
- Attached file dimensions
Not verified
Speed & reliability
About 48.22s end to end in this run; reliability not retested
Detailed facts & historical record
- Timing observation
Network-observed server wait: 48.22s · End-to-end reference: 48.22s
- Date & fixture
2026-11-15 · anchor_transcribe_v1 · US-West (California, AS2914)
- Repeated tests & reliability
No standardized repetition count, success rate or variability range is recorded.
Interaction experience
No login in this run
Detailed facts & historical record
- Account requirements
No login in this test
- Sign-in methods
No login required, full guest access
- Manual adjustment
Not verified
- Interaction observations
Not verified
Background & reputation
Fish Audio (Hanabi AI Inc.) · Long-term reputation not independently verified
Detailed facts & historical record
- Service lifecycle notice
Not verified
- Operator
Fish Audio (Hanabi AI Inc.)
- Recorded origin
Not verified
- Domain history record
Not verified
- Background & reputation assessment
Not verified
- External reputation record
Not verified
Engineering & privacy
Processing location unconfirmed;Explicit retention period unconfirmed; inspect policy record
Detailed facts & historical record
- Processing location
Processing location unconfirmed
- Third-party tracking record
Google Analytics · Cloudflare
- Engineering & privacy assessment
Not verified
- Retention statement
Explicit retention period unconfirmed; inspect policy record
Task free allowance & pricing disclosure
Web tool supports direct single audio file conversion
Clearly shows supported formats prior to upload
Site-wide plans belong to the product node (see Product-level pricing baseline ↑).
Expand site-wide plans aligned for Audio transcription (5 records)
Site-wide TTS, Voice Design, and voice cloning plans on Fish Audio · 2026-11-12
Realistic AI voice synthesis, 3 public voice slots, enhanced voice cloning, no credit card required;500 chars/conv limit, personal non-commercial use only
15,000 chars/conv, unlimited public + 10 private slots, priority queue, Voice Design, commercial rights
15,000 chars/conv, unlimited public + 10 private slots, priority queue, Voice Design, commercial rights
30,000 chars/conv, 3 team seats, unlimited voice slots, 5 pro slots, 7-day refund guarantee
30,000 chars/conv, 3 team seats, unlimited voice slots, 5 pro slots, 7-day refund guarantee
5 plan / billing-period records, all listed; — means that period is not recorded.
Offers Free tier (8K credits/mo, ~7 mins); paid subscriptions include Plus ($15/mo, $66/yr introductory annual) and Pro ($100/mo, $450/yr introductory annual).
Cancellation, sources & verification record
Cancellation and refund terms unverified
Fish Audio Official Homepage & Studio ↗ · 2026-11-12 Capture 1 ↗
Fish Audio Official Pricing & Plans ↗ · 2026-11-12 Capture 1 ↗
Evaluation basis & full scores · Overall 86.9/100
Overall = honesty & reputation × 30% + capability × 70%. Component maxima follow this report’s rubric. List scores are rounded for display; original precision is retained here.
Scoring version 2.3.1 · Test fixture anchor_transcribe_v1
Honesty & reputation · 94/100 · 30%
| Criterion | Score | Rationale | Basis |
|---|---|---|---|
| Pricing transparency | 34 / 35 | Explanation unavailable | Evidence A → |
| Interaction restraint | 28 / 30 | Explanation unavailable | Evidence A → |
| Background & reputation | 18 / 20 | Explanation unavailable | Evidence A → |
| Engineering & privacy | 14 / 15 | Explanation unavailable | Evidence A → |
Capability · 83.8/100 · 70%
| Criterion | Score | Rationale | Basis |
|---|---|---|---|
| Task quality | 57.8 / 65 | Measured anchor metrics: word_accuracy_pct=79.4 · keyword_recall_pct=100 · token_preserved=true · duration_sec=38.9 · text_observed=Fully retained RealTestTranscribeVerified2026 token and all financial figures with 100% recall | Evidence A → |
| Deliverable specifications | 16 / 20 | Clean unwatermarked export (8/8); Export spec: Native TXT text (0.5 KB, 64 words, with speaker labels) | Evidence A → |
| Processing speed | 10 / 15 | Network-observed server wait: 48.22s (API mode: async_poll_verified; network upload 1.5s / end-to-end 48.22s shown for reference only, never penalized) | Evidence A → |
Legacy scores may include advertised maximum capabilities. Read tested output separately from paid capabilities. Records without matching tiers and scope are not ranked together.
Linked capability test: Text to speech
2026-11-15 · Native output attached. Findings cover the recorded fixture and conditions; paid specifications may be untested.
Verified native export & same-run screenshot evidence
Open native exported file (MP3 · Output attached) ↗Task quality
Audio duration 53.05s · Sample rate 44100 Hz · Channels Mono (1ch) · Audio bitrate 128 kbps
Detailed facts & historical record
- Measured fixture results
Audio duration: 53.05s · Sample rate: 44100 Hz · Channels: Mono (1ch) · Audio bitrate: 128 kbps
- Fixture findings
Deterministic acoustic analysis confirms a 53.05s 44.1kHz MP3 file free of watermarks or noise, featuring natural cadence and expressive intonation.
- Original historical observation
Fish Audio studio processes 497-character benchmark text in 4.19s with Drama 3, delivering pristine 44.1kHz MP3 audio free of noise artifacts (01_landing.png, 02_result.png, 03_download.png).
- Suitable uses · historical assessment
Content creators and developers seeking high-fidelity AI voiceover, diverse voices, and open-source customizable workflows
- Result & output evidence
Delivery capabilities
MP3 · Output attached · No watermark in test
Detailed facts & historical record
- Recorded export specifications
MP3 · Output attached · No watermark in test
- Historical specification note · not an official maximum
MP3 audio (829.0 KB · 53.05s · 44.1kHz · 128kbps · watermark-free)
- Watermark observation
Watermark-free
- Batch & API
Supports multi-character dialogue, paragraph segmentation, and official API
- Recorded free-tier dimensions
Not verified
- Attached file dimensions
Not verified
Speed & reliability
About 4.19s end to end in this run; reliability not retested
Detailed facts & historical record
- Timing observation
Network-observed server wait: 4.19s · End-to-end reference: 4.19s
- Date & fixture
2026-11-15 · anchor_tts_v1 · US-West (California, AS2914)
- Repeated tests & reliability
No standardized repetition count, success rate or variability range is recorded.
Interaction experience
Login required in this run
Detailed facts & historical record
- Account requirements
Account required in this test
- Sign-in methods
Supports Google SSO or email; free tier includes 8,000 computation credits monthly
- Manual adjustment
Not verified
- Interaction observations
Studio accepts 497-character benchmark script without gating modals, generating Drama 3 speech in 4.19s with free native audio download.
Background & reputation
Fish Audio Inc. · Long-term reputation not independently verified
Detailed facts & historical record
- Service lifecycle notice
Not verified
- Operator
Fish Audio Inc.
- Recorded origin
Open-source community / International team
- Domain history record
Commercial hosted platform originating from open-source Fish Speech
- Background & reputation assessment
Maintained by the core team behind open-source Fish Speech, providing commercial dual-licensing and hosted infrastructure.
- External reputation record
Acclaimed open-source model with over 20,000 GitHub stars, holding strong technical reputation across the AI voice community.
Engineering & privacy
Uploaded for cloud processing;Explicit retention period unconfirmed; inspect policy record
Detailed facts & historical record
- Processing location
Uploaded for cloud processing
- Third-party tracking record
Google Analytics · Stripe Checkout
- Engineering & privacy assessment
Encrypted HTTPS audio streaming to high-performance inference clusters, supporting multi-segment synthesis and generation history.
- Retention statement
Explicit retention period unconfirmed; inspect policy record
Task free allowance & pricing disclosure
Free tier includes 8,000 credits/mo with a 500-character single generation limit
Character counter 497/500 and model selector clearly visible below text editor
Site-wide plans belong to the product node (see Product-level pricing baseline ↑).
Expand site-wide plans aligned for Text to speech (5 records)
Site-wide TTS, Voice Design, and voice cloning plans on Fish Audio · 2026-11-12
Realistic AI voice synthesis, 3 public voice slots, enhanced voice cloning, no credit card required;500 chars/conv limit, personal non-commercial use only
15,000 chars/conv, unlimited public + 10 private slots, priority queue, Voice Design, commercial rights
15,000 chars/conv, unlimited public + 10 private slots, priority queue, Voice Design, commercial rights
30,000 chars/conv, 3 team seats, unlimited voice slots, 5 pro slots, 7-day refund guarantee
30,000 chars/conv, 3 team seats, unlimited voice slots, 5 pro slots, 7-day refund guarantee
5 plan / billing-period records, all listed; — means that period is not recorded.
Offers Free tier (8K credits/mo, ~7 mins); paid subscriptions include Plus ($15/mo, $66/yr introductory annual) and Pro ($100/mo, $450/yr introductory annual).
Cancellation, sources & verification record
Cancellation and refund terms unverified
Fish Audio Official Homepage & Studio ↗ · 2026-11-12 Capture 1 ↗
Fish Audio Official Pricing & Plans ↗ · 2026-11-12 Capture 1 ↗
Evaluation basis & full scores · Overall 93.7/100
Overall = honesty & reputation × 30% + capability × 70%. Component maxima follow this report’s rubric. List scores are rounded for display; original precision is retained here.
Scoring version 2.3.1 · Test fixture anchor_tts_v1
Honesty & reputation · 93/100 · 30%
| Criterion | Score | Rationale | Basis |
|---|---|---|---|
| Pricing transparency | 33 / 35 | Clearly specifies Free tier with 8,000 monthly credits and 500-char input limit; Plus ($7.50/mo) and Pro ($15/mo) pricing is transparent. | Evidence A → |
| Interaction restraint | 28 / 30 | Studio accepts 497-character benchmark script without gating modals, generating Drama 3 speech in 4.19s with free native audio download. | Evidence A → |
| Background & reputation | 18 / 20 | Maintained by the core team behind open-source Fish Speech, providing commercial dual-licensing and hosted infrastructure. | Evidence A → |
| Engineering & privacy | 14 / 15 | Encrypted HTTPS audio streaming to high-performance inference clusters, supporting multi-segment synthesis and generation history. | Evidence A → |
Capability · 94/100 · 70%
| Criterion | Score | Rationale | Basis |
|---|---|---|---|
| Task quality | 60 / 65 | Deterministic acoustic inspection: Synthesizes 53.05s high-fidelity MP3 audio (within [15.0s, 60.0s] bounds) at 44,100 Hz, 128 kbps, delivering expressive and natural cadence (60.0/65) | Evidence A → |
| Deliverable specifications | 20 / 20 | Direct native download of full 53.05s 44.1kHz MP3 audio file (829.0 KB) free of watermarks or noise (20.0/20) | Evidence A → |
| Processing speed | 14 / 15 | Cloud neural speech generation completes end-to-end in 4.19s, rapidly delivering 53s of synthesized audio (14.0/15) | Evidence A → |
Legacy scores may include advertised maximum capabilities. Read tested output separately from paid capabilities. Records without matching tiers and scope are not ranked together.